INDEX
    Explanations

    subject pronouns

    New Auto-Interp
    Negative Logits
    -0.85
    -0.84
    ↵↵
    -0.83
     (
    -0.67
     -
    -0.66
     [
    -0.63
      
    -0.60
    <eos>
    -0.58
    --
    -0.57
     --
    -0.57
    POSITIVE LOGITS
     nahilalakip
    1.28
    mybatisplus
    1.26
     wireType
    1.16
     Мексичка
    1.13
    Diwedd
    1.12
    دانشنامهٔ
    1.11
     resourceCulture
    1.11
    AddHtmlAttribute
    1.09
    SequentialGroup
    1.09
    تقاوى
    1.06
    Act Density 0.042%

    No Known Activations