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

    Neuronpedia

    INDEX
    Explanations

    book titles

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of books or guides

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asio
    -0.76
    itcher
    -0.63
     throats
    -0.63
    sembly
    -0.62
     undecided
    -0.61
    ntil
    -0.60
     vibrant
    -0.59
     twitch
    -0.59
     territ
    -0.59
    querade
    -0.58
    POSITIVE LOGITS
    book
    1.30
    marks
    1.08
    books
    1.07
    shop
    1.04
    worm
    1.01
    DragonMagazine
    0.99
    stores
    0.97
    eers
    0.97
    eer
    0.91
    worms
    0.90
    Act Density 0.017%

    No Known Activations