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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numbers and hyphenated ranges

    oai_token-act-pair · gpt-3.5-turbo

    references to the length or number of pages in documents or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Claus
    -0.74
     Warfare
    -0.71
     warmer
    -0.67
     reborn
    -0.66
     recapt
    -0.64
     machinery
    -0.63
     faire
    -0.63
     Dress
    -0.63
     colder
    -0.63
     Festival
    -0.62
    POSITIVE LOGITS
     pages
    1.77
    page
    1.60
     paragraphs
    1.54
    pages
    1.44
    paragraph
    1.41
     page
    1.36
     paragraph
    1.30
    Pages
    1.26
     Pages
    1.21
     sentences
    1.16
    Act Density 0.151%

    No Known Activations