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

    Neuronpedia

    INDEX
    Explanations

    references to chapters and storytelling elements in written works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    book chapters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.90
    ftagPool
    -0.67
    AndEndTag
    -0.64
     مرئيه
    -0.63
    ValueStyle
    -0.58
    SOUNDBITE
    -0.56
     وتسجيلات
    -0.55
     surla
    -0.55
    IBOutlet
    -0.54
     wireType
    -0.54
    POSITIVE LOGITS
     chapter
    0.94
     chapters
    0.93
    chapter
    0.88
     Chapter
    0.85
    chapters
    0.82
    Chapter
    0.82
     chapitre
    0.76
     Chapters
    0.74
    Chapters
    0.72
     Kapitel
    0.70
    Act Density 0.061%

    No Known Activations