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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bound
    -0.74
     sarcastic
    -0.71
     cryst
    -0.71
     crest
    -0.70
     bloodstream
    -0.68
     corrid
    -0.68
     millennials
    -0.68
     gearing
    -0.67
     casualty
    -0.66
     scra
    -0.66
    POSITIVE LOGITS
    jen
    1.10
    zyk
    1.05
    owsky
    1.03
    aja
    0.97
    én
    0.97
    owski
    0.95
    orst
    0.93
    eus
    0.93
    zinski
    0.92
    oulos
    0.91
    Act Density 0.200%

    No Known Activations