INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    anche
    -0.08
    ampoline
    -0.08
     treatments
    -0.08
     clinical
    -0.07
    -0.07
    may
    -0.07
     parasites
    -0.07
     elucid
    -0.07
    -0.07
    疫情
    -0.07
    POSITIVE LOGITS
     Sache
    0.10
     горизонт
    0.09
     Bast
    0.09
     сторона
    0.09
    heer
    0.08
    iaan
    0.08
     barg
    0.08
     Amal
    0.08
     åt
    0.08
     Sard
    0.08
    Act Density 0.003%

    No Known Activations