INDEX
    Explanations

    numeric data and statistics

    New Auto-Interp
    Negative Logits
    essenger
    -0.16
    embros
    -0.16
     полÑı
    -0.14
    yı
    -0.14
    adows
    -0.14
    _macros
    -0.14
    891
    -0.14
    imizi
    -0.14
    Ñľ
    -0.13
    890
    -0.13
    POSITIVE LOGITS
     exempt
    0.16
    spb
    0.15
    onta
    0.14
    ÙĴد
    0.14
    óm
    0.13
    uai
    0.13
     intr
    0.13
     Yan
    0.13
    ruk
    0.13
     extr
    0.13
    Act Density 0.172%

    No Known Activations