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

    Neuronpedia

    INDEX
    Explanations

    statements of fact or truth

    oai_token-act-pair · gpt-3.5-turbo

    statements that refer to factual information or opinions about societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addon
    -0.81
    bably
    -0.74
    arnaev
    -0.73
    Dispatch
    -0.71
    etsk
    -0.70
    afort
    -0.69
    iciary
    -0.67
    éĹĺ
    -0.66
    ulet
    -0.65
    ãĥĩ
    -0.64
    POSITIVE LOGITS
     psychologists
    1.06
    Many
    1.03
    Studies
    0.98
     women
    0.96
     Many
    0.96
     many
    0.95
     females
    0.95
    Women
    0.94
     people
    0.94
     males
    0.93
    Act Density 0.730%

    No Known Activations