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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word 'Book'

    oai_token-act-pair · gpt-3.5-turbo

    references to "Book" in various contexts, particularly highlighting its significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rad
    -0.78
    rity
    -0.75
     gren
    -0.73
     saline
    -0.72
    fps
    -0.70
     stro
    -0.70
     watts
    -0.68
     respir
    -0.67
     externalToEVAOnly
    -0.66
     drain
    -0.64
    POSITIVE LOGITS
     Book
    3.83
    Book
    2.81
     BOOK
    2.33
    book
    2.27
     book
    2.10
     Books
    2.08
    BOOK
    2.04
    books
    1.81
     books
    1.73
    Books
    1.71
    Act Density 0.013%

    No Known Activations