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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific page numbers within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of pages in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     equ
    -0.79
     receivers
    -0.77
     con
    -0.72
     coron
    -0.68
     lows
    -0.67
     trough
    -0.66
     equip
    -0.66
     cop
    -0.64
     highs
    -0.64
     flu
    -0.64
    POSITIVE LOGITS
    page
    4.06
    pages
    2.38
    Page
    2.30
     page
    2.12
     pages
    1.95
     Page
    1.90
    Pages
    1.85
     PAGE
    1.72
    paragraph
    1.69
     Pages
    1.66
    Act Density 0.012%

    No Known Activations