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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "bun"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of buns and related imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Import
    -0.73
    士
    -0.70
     Archdemon
    -0.70
    Ö¼
    -0.70
     Emin
    -0.68
    ences
    -0.68
     Grave
    -0.64
    endale
    -0.64
    ENC
    -0.64
    ONS
    -0.63
    POSITIVE LOGITS
    yip
    1.29
    gee
    1.09
    ches
    1.08
    ting
    1.05
    kered
    1.03
    ters
    0.99
    uates
    0.95
    terness
    0.91
    hered
    0.91
    ched
    0.88
    Act Density 0.037%

    No Known Activations