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

    Neuronpedia

    INDEX
    Explanations

    the word "Wow"

    oai_token-act-pair · gpt-4-turbo

    exclamations of surprise or admiration

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or amazement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andro
    -0.83
     delinqu
    -0.72
    ":[{"
    -0.69
    unal
    -0.69
     kindred
    -0.68
    icipated
    -0.67
    utions
    -0.67
    ossession
    -0.66
    ugal
    -0.65
    */(
    -0.65
    POSITIVE LOGITS
     Wow
    1.14
    orld
    0.96
    ards
    0.95
    Wow
    0.95
    zers
    0.93
     wow
    0.90
    wow
    0.88
    yssey
    0.80
    biz
    0.79
    herty
    0.77
    Act Density 0.013%

    No Known Activations