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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to the length of written documents

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of pages in texts or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALLY
    -0.91
     theirs
    -0.70
    oise
    -0.69
    CAST
    -0.67
    RANT
    -0.67
    xon
    -0.66
    REM
    -0.63
     preschool
    -0.62
    earned
    -0.61
     Helsinki
    -0.61
    POSITIVE LOGITS
     pages
    1.41
    pages
    1.20
    Pages
    1.04
    page
    1.00
     Pages
    0.95
     page
    0.94
    antry
    0.94
    views
    0.92
     chapters
    0.88
     pg
    0.85
    Act Density 0.008%

    No Known Activations