INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     تكون
    0.87
     }(\
    0.82
    كون
    0.82
    idone
    0.80
    0.80
    umuz
    0.79
    کیا
    0.78
    sse
    0.77
     рассказыва
    0.77
    0.77
    POSITIVE LOGITS
    bait
    1.35
     heels
    1.26
    dokter
    1.14
     anywhere
    1.14
     hereto
    1.05
     tombol
    1.03
     nbfs
    1.03
     einmal
    1.00
    )="
    0.97
     buttons
    0.97
    Act Density 0.028%

    No Known Activations