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

    Neuronpedia

    INDEX
    Explanations

    references to specific chapters in a book or document

    oai_token-act-pair · gpt-3.5-turbo

    references to chapters in books or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    axter
    -0.83
    berman
    -0.74
    eco
    -0.72
    toe
    -0.69
    aces
    -0.68
     vot
    -0.67
    oles
    -0.67
     bolts
    -0.67
    enez
    -0.66
     fitt
    -0.66
    POSITIVE LOGITS
    Chapter
    1.05
     Chapter
    1.05
     Chapters
    0.97
    CHAPTER
    0.90
    ĸļ
    0.89
     Prol
    0.87
    APTER
    0.85
    ĨĴ
    0.84
     Transcript
    0.82
    chapter
    0.81
    Act Density 0.005%

    No Known Activations