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

    Neuronpedia

    INDEX
    Explanations

    chapter numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific chapters in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzle
    -0.75
    oggles
    -0.73
    yg
    -0.70
    pes
    -0.69
    berman
    -0.68
     blaster
    -0.66
    enez
    -0.66
    fitting
    -0.66
     fitt
    -0.65
    ydia
    -0.65
    POSITIVE LOGITS
    ĸļ
    0.95
     chapter
    0.92
     chapters
    0.84
    apeake
    0.83
    chapter
    0.81
    hound
    0.76
     Chapter
    0.75
    icularly
    0.75
     Chapters
    0.73
    CHAPTER
    0.72
    Act Density 0.015%

    No Known Activations