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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Support
    -0.08
    Hold
    -0.08
    鹠
    -0.07
    .Keyword
    -0.07
    걀
    -0.07
    新年
    -0.07
    个
    -0.07
    rends
    -0.07
     стандарт
    -0.07
    realDonaldTrump
    -0.07
    POSITIVE LOGITS
    .vec
    0.07
     الأه
    0.07
     предпоч
    0.07
    铰
    0.07
     Vy
    0.07
     tec
    0.06
    Pie
    0.06
    .rpc
    0.06
    _REV
    0.06
    京城
    0.06
    Act Density 0.013%

    No Known Activations