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

    Neuronpedia

    INDEX
    Explanations

    references to chapters and sections in a document

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

    "chapter" or "chapters"

    np_acts-logits-general · gemini-2.0-flash

    chapter followed by number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consenti
    -0.61
    rosse
    -0.53
    ا
    -0.49
     ose
    -0.49
     Grin
    -0.49
    eri
    -0.49
    GPI
    -0.49
    ole
    -0.48
    yntaxException
    -0.48
     Tind
    -0.47
    POSITIVE LOGITS
     chapters
    1.04
     chapter
    1.03
     Chapters
    1.01
    Chapters
    0.95
    chapter
    0.95
    chapters
    0.94
     Chapter
    0.94
    Chapter
    0.90
     CHAPTER
    0.90
    expandindo
    0.89
    Act Density 0.126%

    No Known Activations