Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ethnicities or nationalities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Regulation
    -0.76
     Bezos
    -0.74
     dossier
    -0.71
     suggestion
    -0.68
     manufact
    -0.68
     recommendation
    -0.67
     dissemination
    -0.67
     effectiveness
    -0.67
     IPM
    -0.66
     playbook
    -0.66
    POSITIVE LOGITS
     minorities
    1.08
    married
    1.00
     alike
    1.00
    aucas
    0.97
     genders
    0.91
     spouses
    0.89
     independents
    0.88
     elderly
    0.88
     Protestants
    0.87
     immigrants
    0.86
    Act Density 0.512%

    No Known Activations