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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    听取
    -0.07
    liğinde
    -0.07
    "—
    -0.07
    륙
    -0.07
     شب
    -0.07
    .In
    -0.07
    (entries
    -0.07
     {-
    -0.07
     Libre
    -0.07
    Bg
    -0.07
    POSITIVE LOGITS
    hello
    0.08
    Anim
    0.08
    תופעה
    0.07
     cosas
    0.07
     soph
    0.07
    ErrorHandler
    0.07
    该怎么办
    0.06
     отношения
    0.06
    푼
    0.06
    不合适
    0.06
    Act Density 0.044%

    No Known Activations