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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of the word "document."

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.85
    cffffcc
    -0.78
    cffff
    -0.76
    ategory
    -0.74
    uyomi
    -0.71
    Stars
    -0.71
    eatures
    -0.70
    awar
    -0.70
    nen
    -0.69
    NetMessage
    -0.69
    POSITIVE LOGITS
    arians
    1.24
    arian
    1.09
    ually
    1.07
     detailing
    0.92
     document
    0.91
     outlining
    0.90
     documents
    0.90
    uments
    0.88
    aries
    0.88
    herty
    0.86
    Act Density 0.056%

    No Known Activations