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

    Neuronpedia

    INDEX
    Explanations

    dates or numbered pages mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to page numbers in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dayName
    -0.85
    ALLY
    -0.80
    ivity
    -0.72
    CAST
    -0.70
    eware
    -0.70
    ivari
    -0.70
    fitted
    -0.69
    itability
    -0.67
    worthiness
    -0.65
    thouse
    -0.63
    POSITIVE LOGITS
    Page
    1.02
     Page
    1.00
    antry
    0.96
    views
    0.84
    page
    0.77
     subp
    0.74
     Pages
    0.73
    ogue
    0.71
    witz
    0.68
     pages
    0.67
    Act Density 0.008%

    No Known Activations