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

    Neuronpedia

    INDEX
    Explanations

    references to PDF files within a document

    oai_token-act-pair · gpt-3.5-turbo

    references to PDF documents and files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    places
    -0.85
    powers
    -0.79
    venge
    -0.79
    hma
    -0.78
    alty
    -0.77
    acha
    -0.77
    allow
    -0.76
    dinand
    -0.76
    tackle
    -0.75
    place
    -0.75
    POSITIVE LOGITS
    PDF
    1.09
     PDF
    1.00
    DragonMagazine
    0.86
     eBook
    0.82
    TeX
    0.81
     document
    0.80
     documents
    0.77
     pdf
    0.77
    IFF
    0.76
     ebook
    0.75
    Act Density 0.016%

    No Known Activations