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

    Neuronpedia

    INDEX
    Explanations

    instances of specific page numbers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the number of pages in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oÄŁ
    -0.76
    alty
    -0.71
    ALLY
    -0.70
    ereo
    -0.70
    ignty
    -0.68
    igham
    -0.67
    xon
    -0.65
    rived
    -0.65
    ratulations
    -0.64
    CAST
    -0.64
    POSITIVE LOGITS
     pages
    1.04
    pages
    0.98
    antry
    0.93
    books
    0.91
    Pages
    0.87
     pg
    0.83
    views
    0.83
    book
    0.82
    worm
    0.80
     Pages
    0.79
    Act Density 0.017%

    No Known Activations