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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names like "Val" or "Valley"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    pread
    -1.42
    rodu
    -1.16
    ģĸ
    -1.03
     Taiwanese
    -1.03
    sein
    -0.99
     Employ
    -0.97
    é¾įå¥ij士
    -0.97
    éĹĺ
    -0.96
    steps
    -0.95
    riad
    -0.95
    POSITIVE LOGITS
    idation
    1.74
    ueless
    1.56
    ibr
    1.53
    idated
    1.53
    uations
    1.51
    uation
    1.49
    uable
    1.48
    idity
    1.32
    mented
    1.32
    entin
    1.30
    Act Density 1.579%

    No Known Activations