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

    Neuronpedia

    INDEX
    Explanations

    mentions of books or textual content within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Book" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rad
    -0.72
     hops
    -0.72
     Cran
    -0.69
     sprink
    -0.69
     gest
    -0.67
     invasive
    -0.65
     pulse
    -0.65
     pumping
    -0.65
     vul
    -0.64
     DHS
    -0.63
    POSITIVE LOGITS
    Book
    4.27
    BOOK
    2.80
    book
    2.47
    Books
    2.14
    books
    2.12
     Book
    2.05
     BOOK
    1.79
    ebook
    1.58
     book
    1.53
     Books
    1.36
    Act Density 0.009%

    No Known Activations