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

    Neuronpedia

    INDEX
    Explanations

    mentions of quantities or numbers

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a count or frequency of occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Despair
    -0.66
    obin
    -0.60
    missible
    -0.60
    agate
    -0.59
     Doodle
    -0.59
    Reviewed
    -0.58
    vation
    -0.57
    sburgh
    -0.56
    amaru
    -0.55
     silence
    -0.55
    POSITIVE LOGITS
     of
    1.06
    Of
    0.82
    of
    0.72
     Of
    0.71
     OF
    0.69
     distributions
    0.66
    dozen
    0.66
    assian
    0.65
    istical
    0.64
    OF
    0.63
    Act Density 0.045%

    No Known Activations