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

    Neuronpedia

    INDEX
    Explanations

    mentions of a particular name

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific letters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     innocence
    -0.71
     Tsukuyomi
    -0.64
     disgust
    -0.63
     tresp
    -0.63
    auga
    -0.62
     spilled
    -0.62
    chwitz
    -0.61
     Tend
    -0.60
     hover
    -0.60
    $$$$
    -0.59
    POSITIVE LOGITS
    mony
    0.77
    andowski
    0.75
    atives
    0.75
    ths
    0.75
    idation
    0.74
    scription
    0.72
    thal
    0.71
    Nic
    0.71
    anium
    0.68
    quer
    0.68
    Act Density 0.092%

    No Known Activations