bbq:subject=all,method=multiple_choice_joint,model=cohere_medium-20221108 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=cohere_small-20220720 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=cohere_xlarge-20220609 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=cohere_xlarge-20221108 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=microsoft_TNLGv2_530B | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=microsoft_TNLGv2_7B | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=openai_ada | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=openai_babbage | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=openai_curie | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=openai_davinci | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=openai_gpt-3.5-turbo-0301 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=openai_text-ada-001 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=openai_text-babbage-001 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=openai_text-curie-001 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=openai_text-davinci-002 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=openai_text-davinci-003 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_bloom | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_glm,stop=hash | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_gpt-j-6b | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_gpt-neox-20b | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_opt-175b | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_opt-66b | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_redpajama-incite-base-3b-v1 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_t0pp,stop=hash | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_t5-11b,stop=hash | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_ul2,stop=hash,global_prefix=nlg | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=together_yalm | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=writer_palmyra-instruct-30 | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_joint,model=writer_palmyra-x | multiple_choice_joint |
bbq:subject=all,method=multiple_choice_separate_calibrated,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
bbq:subject=all,method=multiple_choice_separate_calibrated,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
bbq:subject=all,method=multiple_choice_separate_calibrated,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
bbq:subject=all,method=multiple_choice_separate_calibrated,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
bbq:subject=all,method=multiple_choice_separate_calibrated,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
bbq:subject=all,method=multiple_choice_separate_calibrated,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
bbq:subject=all,method=multiple_choice_separate_original,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_separate_original |
bbq:subject=all,method=multiple_choice_separate_original,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_separate_original |
bbq:subject=all,method=multiple_choice_separate_original,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_separate_original |
bbq:subject=all,method=multiple_choice_separate_original,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_separate_original |
bbq:subject=all,method=multiple_choice_separate_original,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_separate_original |
bbq:subject=all,method=multiple_choice_separate_original,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_joint,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=binding,method=multiple_choice_joint,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=binding,method=multiple_choice_joint,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=binding,method=multiple_choice_joint,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=binding,method=multiple_choice_joint,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=binding,method=multiple_choice_joint,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=binding,method=multiple_choice_separate_calibrated,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=binding,method=multiple_choice_separate_calibrated,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=binding,method=multiple_choice_separate_calibrated,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=binding,method=multiple_choice_separate_calibrated,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=binding,method=multiple_choice_separate_calibrated,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=binding,method=multiple_choice_separate_calibrated,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=ai21_j1-grande | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=ai21_j1-grande-v2-beta | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=ai21_j1-jumbo | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=ai21_j1-large | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=ai21_j2-grande | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=ai21_j2-jumbo | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=ai21_j2-large | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=anthropic_stanford-online-all-v4-s3 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=cohere_command-medium-beta | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=cohere_command-xlarge-beta | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=cohere_large-20220720 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=cohere_medium-20220720 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=cohere_medium-20221108 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=cohere_small-20220720 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=cohere_xlarge-20220609 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=cohere_xlarge-20221108 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=microsoft_TNLGv2_530B | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=microsoft_TNLGv2_7B | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=openai_ada | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=openai_babbage | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=openai_curie | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=openai_davinci | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=openai_text-ada-001 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=openai_text-babbage-001 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=openai_text-curie-001 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=openai_text-davinci-002 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=openai_text-davinci-003 | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=together_bloom | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=together_gpt-j-6b | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=together_gpt-neox-20b | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=together_opt-175b | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=together_opt-66b | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=binding,method=multiple_choice_separate_original,model=together_redpajama-incite-base-3b-v1 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_joint,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=irregular_forms,method=multiple_choice_joint,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=irregular_forms,method=multiple_choice_joint,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=irregular_forms,method=multiple_choice_joint,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=irregular_forms,method=multiple_choice_joint,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=irregular_forms,method=multiple_choice_joint,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_calibrated,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_calibrated,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_calibrated,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_calibrated,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_calibrated,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_calibrated,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=ai21_j1-grande | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=ai21_j1-grande-v2-beta | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=ai21_j1-jumbo | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=ai21_j1-large | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=ai21_j2-grande | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=ai21_j2-jumbo | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=ai21_j2-large | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=anthropic_stanford-online-all-v4-s3 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=cohere_command-medium-beta | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=cohere_command-xlarge-beta | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=cohere_large-20220720 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=cohere_medium-20220720 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=cohere_medium-20221108 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=cohere_small-20220720 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=cohere_xlarge-20220609 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=cohere_xlarge-20221108 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=microsoft_TNLGv2_530B | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=microsoft_TNLGv2_7B | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=openai_ada | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=openai_babbage | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=openai_curie | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=openai_davinci | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=openai_text-ada-001 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=openai_text-babbage-001 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=openai_text-curie-001 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=openai_text-davinci-002 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=openai_text-davinci-003 | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=together_bloom | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=together_gpt-j-6b | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=together_gpt-neox-20b | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=together_opt-175b | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=together_opt-66b | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=irregular_forms,method=multiple_choice_separate_original,model=together_redpajama-incite-base-3b-v1 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_joint,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=island_effects,method=multiple_choice_joint,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=island_effects,method=multiple_choice_joint,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=island_effects,method=multiple_choice_joint,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=island_effects,method=multiple_choice_joint,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=island_effects,method=multiple_choice_joint,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_joint |
blimp:phenomenon=island_effects,method=multiple_choice_separate_calibrated,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=island_effects,method=multiple_choice_separate_calibrated,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=island_effects,method=multiple_choice_separate_calibrated,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=island_effects,method=multiple_choice_separate_calibrated,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=island_effects,method=multiple_choice_separate_calibrated,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=island_effects,method=multiple_choice_separate_calibrated,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_separate_calibrated |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=ai21_j1-grande | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=ai21_j1-grande-v2-beta | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=ai21_j1-jumbo | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=ai21_j1-large | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=ai21_j2-grande | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=ai21_j2-jumbo | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=ai21_j2-large | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=anthropic_stanford-online-all-v4-s3 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=cohere_command-medium-beta | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=cohere_command-xlarge-beta | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=cohere_large-20220720 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=cohere_medium-20220720 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=cohere_medium-20221108 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=cohere_small-20220720 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=cohere_xlarge-20220609 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=cohere_xlarge-20221108 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=microsoft_TNLGv2_530B | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=microsoft_TNLGv2_7B | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=openai_ada | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=openai_babbage | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=openai_curie | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=openai_davinci | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=openai_text-ada-001 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=openai_text-babbage-001 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=openai_text-curie-001 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=openai_text-davinci-002 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=openai_text-davinci-003 | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=together_bloom | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=together_bloom,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=together_gpt-j-6b | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=together_gpt-j-6b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=together_gpt-neox-20b | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=together_gpt-neox-20b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=together_opt-175b | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=together_opt-175b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=together_opt-66b | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=together_opt-66b,groups=ablation_multiple_choice | multiple_choice_separate_original |
blimp:phenomenon=island_effects,method=multiple_choice_separate_original,model=together_redpajama-incite-base-3b-v1 | multiple_choice_separate_original |
blimp:phenomenon=quantifiers,method=multiple_choice_joint,model=anthropic_stanford-online-all-v4-s3,groups=ablation_multiple_choice | multiple_choice_joint |