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

    Neuronpedia

    INDEX
    Explanations

    mentions of books or book-related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    00200000
    -0.72
     Yin
    -0.70
    ilitary
    -0.68
     Bots
    -0.63
     VIDEOS
    -0.62
    hod
    -0.60
     Diaz
    -0.60
     distant
    -0.60
     twitch
    -0.60
     Santiago
    -0.59
    POSITIVE LOGITS
    stores
    1.54
    marks
    1.40
    seller
    1.32
    shop
    1.28
    worm
    1.28
    marked
    1.22
    worms
    1.21
    keeping
    1.19
    sell
    1.12
    cases
    1.11
    Act Density 0.093%

    No Known Activations