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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    LE
    0.88
     всех
    0.84
     поводу
    0.81
     правительства
    0.80
    etzt
    0.80
    SH
    0.79
    NE
    0.79
     انہیں
    0.79
     способов
    0.79
    /=
    0.78
    POSITIVE LOGITS
    ча
    1.07
    <0x80>
    1.02
    a
    0.94
    matik
    0.93
    mother
    0.92
    ﺴ
    0.92
    ยังมี
    0.90
    ﯿ
    0.90
    本身
    0.90
    訥
    0.90
    Act Density 0.017%

    No Known Activations