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

    Neuronpedia

    INDEX
    Explanations

    mentions of minority groups

    oai_token-act-pair · gpt-3.5-turbo

    references to minority groups and their issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hran
    -0.86
    DCS
    -0.86
    lov
    -0.85
    atche
    -0.82
    sis
    -0.80
    æ©
    -0.78
    hiba
    -0.77
    ensional
    -0.75
    rir
    -0.75
    dra
    -0.71
    POSITIVE LOGITS
     minority
    0.93
     minorities
    0.83
     genders
    0.81
     males
    0.81
     populations
    0.78
     quarters
    0.77
    ativity
    0.76
     groups
    0.74
     peoples
    0.73
     faiths
    0.72
    Act Density 0.014%

    No Known Activations