INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    athan
    -0.08
    Extent
    -0.08
     monoc
    -0.07
     quart
    -0.07
     пер
    -0.07
     Bla
    -0.07
    pedo
    -0.07
    вы
    -0.07
    Lobby
    -0.07
     anteced
    -0.06
    POSITIVE LOGITS
     कराया
    0.10
    ငံ
    0.09
     للت
    0.09
     לי
    0.09
     gesteld
    0.08
    خصصة
    0.08
     виду
    0.08
    Glad
    0.08
    0.08
     IJ
    0.08
    Act Density 0.029%

    No Known Activations