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

    Neuronpedia

    INDEX
    Explanations

    proper names or nouns representing individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly in professional or notable contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertisement
    -0.77
    conservancy
    -0.73
    ¥µ
    -0.72
    ombat
    -0.71
    actionDate
    -0.71
    duration
    -0.69
    peed
    -0.68
    qqa
    -0.68
    category
    -0.67
    fal
    -0.67
    POSITIVE LOGITS
    's
    0.94
     Doe
    0.90
     remembers
    0.89
     enjoys
    0.88
     was
    0.87
     knows
    0.86
     recalls
    0.85
     Sr
    0.85
     wears
    0.82
     prefers
    0.82
    Act Density 0.232%

    No Known Activations