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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    isicing
    -0.07
     Local
    -0.07
     cared
    -0.07
    appearance
    -0.07
     wła
    -0.07
    WindowText
    -0.07
    External
    -0.07
    _d
    -0.06
    stores
    -0.06
     Implicit
    -0.06
    POSITIVE LOGITS
     προσ
    0.07
     accordingly
    0.06
    ////////////
    0.06
    如下
    0.06
    VN
    0.06
    یدا
    0.06
    ulması
    0.06
    имость
    0.06
     Ник
    0.06
     //////////////////
    0.06
    Act Density 0.002%

    No Known Activations