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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    grese
    -0.08
     Integer
    -0.08
     Object
    -0.07
    -proof
    -0.07
    lug
    -0.07
    一脸
    -0.07
    factory
    -0.07
    book
    -0.06
     resumes
    -0.06
    ﮃ
    -0.06
    POSITIVE LOGITS
    .win
    0.08
     Kul
    0.08
    _rt
    0.08
    getContent
    0.07
    .dec
    0.07
    蝉
    0.07
    (bs
    0.07
     колл
    0.07
     chol
    0.07
    鲁迅
    0.07
    Act Density 0.003%

    No Known Activations