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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reading and books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bottled
    -0.16
    ünst
    -0.14
     Tub
    -0.14
    YouTube
    -0.14
    åłĤ
    -0.14
    reator
    -0.14
    ä¿Ĭ
    -0.14
    ati
    -0.13
     Garland
    -0.13
    ESIS
    -0.13
    POSITIVE LOGITS
     reading
    0.32
     Reading
    0.29
    Reading
    0.28
    reading
    0.26
    READING
    0.23
     Books
    0.23
     books
    0.22
     library
    0.22
    reads
    0.22
     bookstore
    0.22
    Act Density 0.278%

    No Known Activations