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

    Neuronpedia

    INDEX
    Explanations

    names and titles related to international figures and officials

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals, places, and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.72
     critical
    -0.66
     sarcastic
    -0.66
     largeDownload
    -0.62
     distinctive
    -0.61
     magnification
    -0.60
     priceless
    -0.60
     cytok
    -0.60
     sudden
    -0.59
     polar
    -0.59
    POSITIVE LOGITS
    ich
    1.03
    ius
    0.98
    eta
    0.91
    ovich
    0.91
    ichi
    0.90
    akis
    0.89
    chuk
    0.88
    inski
    0.88
    ovic
    0.86
    lette
    0.86
    Act Density 1.144%

    No Known Activations