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

    Neuronpedia

    INDEX
    Explanations

    references to documents, records, or any form of textual information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barton
    -0.17
    Ñĩай
    -0.16
     Bernstein
    -0.16
     Barker
    -0.15
     Barnett
    -0.15
     Baldwin
    -0.15
     Bowman
    -0.15
    BIT
    -0.15
    /bit
    -0.14
     Bethlehem
    -0.14
    POSITIVE LOGITS
     book
    0.88
    -book
    0.71
    book
    0.71
     books
    0.71
     Book
    0.66
     BOOK
    0.65
    Book
    0.64
    _book
    0.63
    书
    0.58
     кни
    0.57
    Act Density 0.251%

    No Known Activations