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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly surnames

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their associated actions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olkien
    -0.73
    iveness
    -0.70
     Polo
    -0.70
     Bombay
    -0.69
    iddler
    -0.67
     Leia
    -0.67
    hirt
    -0.67
    ertodd
    -0.66
    ocene
    -0.65
     Hindi
    -0.63
    POSITIVE LOGITS
    rolet
    0.72
    hower
    0.71
    auts
    0.70
    etary
    0.69
    lest
    0.66
    agraph
    0.65
    flies
    0.64
    oleon
    0.63
    atell
    0.63
    nai
    0.62
    Act Density 0.049%

    No Known Activations