INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    stood
    -0.91
     Vase
    -0.81
    isations
    -0.71
    Vase
    -0.69
    исленность
    -0.69
     Soldiers
    -0.68
     inclination
    -0.66
    nefs
    -0.66
     محفوظة
    -0.65
    izations
    -0.64
    POSITIVE LOGITS
     autorytatywna
    0.52
    mbol
    0.48
    gge
    0.47
    parsedMessage
    0.46
    AnchorTagHelper
    0.44
    ndorf
    0.44
    tor
    0.44
     Per
    0.44
    ,
    0.44
    oa̍t
    0.44
    Act Density 1.581%

    No Known Activations