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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogene
    -0.74
     366
    -0.70
    ogen
    -0.70
    {"
    -0.70
     285
    -0.69
     295
    -0.68
    ANA
    -0.68
    cards
    -0.67
    ãĥĸ
    -0.67
     296
    -0.66
    POSITIVE LOGITS
    س
    0.89
    09
    0.77
    12
    0.76
     Hollande
    0.71
    08
    0.71
    reys
    0.70
    shift
    0.67
    Shift
    0.67
    ¹
    0.66
     Weld
    0.66
    Act Density 1.093%

    No Known Activations