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

    Neuronpedia

    INDEX
    Explanations

    mentions of books

    oai_token-act-pair · gpt-3.5-turbo

    references to books and their accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    00200000
    -0.74
     Yin
    -0.70
    alty
    -0.67
     Normandy
    -0.66
     saline
    -0.63
     Security
    -0.63
     Vital
    -0.63
     Bots
    -0.62
    assis
    -0.62
    ntil
    -0.60
    POSITIVE LOGITS
    stores
    1.33
    marks
    1.12
    books
    1.11
    worms
    1.06
    hel
    1.05
     books
    0.97
    shop
    0.97
    poons
    0.95
    book
    0.94
    marked
    0.93
    Act Density 0.028%

    No Known Activations