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

    Neuronpedia

    INDEX
    Explanations

    capital letter 'C' characters with ASCII codes 10 and 7

    oai_token-act-pair · gpt-3.5-turbo

    strong emotional expressions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acebook
    -0.76
    uese
    -0.75
    hement
    -0.72
    ulkan
    -0.72
    utical
    -0.72
    xual
    -0.71
    nesday
    -0.70
    ividual
    -0.69
    ensibly
    -0.68
    abwe
    -0.68
    POSITIVE LOGITS
    Unless
    0.91
    ³³³
    0.87
    Reader
    0.87
    Whether
    0.85
    Rated
    0.83
    If
    0.83
    Anyway
    0.83
    Trivia
    0.83
    Scroll
    0.83
    Advertisement
    0.82
    Act Density 0.309%

    No Known Activations