INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     quorum
    -0.09
     Pair
    -0.09
     before
    -0.09
     exemplar
    -0.08
     One
    -0.08
     delayed
    -0.08
     pair
    -0.08
     trước
    -0.07
     esem
    -0.07
     sebelum
    -0.07
    POSITIVE LOGITS
    urezza
    0.08
     varn
    0.08
    ulem
    0.08
    cta
    0.08
    @mail
    0.08
     luft
    0.08
    0.08
    erdas
    0.07
    pegno
    0.07
    akkat
    0.07
    Act Density 0.000%

    No Known Activations