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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words

    oai_token-act-pair · gpt-3.5-turbo

    references to interpersonal or social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongyang
    -0.72
    ĨĴ
    -0.72
     Nare
    -0.72
     Corpus
    -0.71
    ĸļ
    -0.70
    edIn
    -0.70
     nomine
    -0.70
    vier
    -0.68
    ħĭ
    -0.66
     Tig
    -0.64
    POSITIVE LOGITS
    exec
    0.85
    gallery
    0.85
    advertising
    0.84
    trade
    0.84
    distance
    0.80
    death
    0.80
    politics
    0.79
    committee
    0.78
    two
    0.77
    usual
    0.76
    Act Density 0.029%

    No Known Activations