INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     as
    -1.18
     консер
    -0.90
     Некоторые
    -0.84
     Особенно
    -0.83
    というのも
    -0.83
     chuyền
    -0.82
     some
    -0.79
    がありません
    -0.78
    Long
    -0.78
     similarly
    -0.76
    POSITIVE LOGITS
     alot
    1.47
    alot
    1.41
     большое
    1.21
     beaucoup
    1.18
     anyway
    1.05
     lot
    1.05
    มาก
    1.00
     всичко
    0.98
     nhiều
    0.96
     مرة
    0.94
    Act Density 0.026%

    No Known Activations