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

    instances of "ok" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oire
    -0.68
     lav
    -0.67
    bugs
    -0.63
    Arcade
    -0.63
    builders
    -0.62
     Legions
    -0.61
    RESULTS
    -0.61
    WHERE
    -0.60
    icone
    -0.60
     cows
    -0.59
    POSITIVE LOGITS
    unin
    1.12
    lahoma
    1.10
    awaru
    1.00
    nown
    0.95
    lass
    0.89
    wana
    0.88
    ettle
    0.88
    arak
    0.88
    ileaks
    0.86
    uments
    0.85
    Act Density 0.027%

    No Known Activations