INDEX
    Explanations

    verb suffixes

    New Auto-Interp
    Negative Logits
     Gegen
    -0.08
     Revival
    -0.08
     Kurt
    -0.08
    antwoord
    -0.08
     Gull
    -0.07
     SU
    -0.07
     Polyn
    -0.07
     Graduate
    -0.07
     Lis
    -0.07
    zky
    -0.07
    POSITIVE LOGITS
    ­ment
    0.10
    ings
    0.10
    -able
    0.10
    ­ing
    0.10
    ments
    0.09
    -your
    0.09
     کردن
    0.09
    -yourself
    0.09
    િંગ
    0.08
    able
    0.08
    Act Density 0.280%

    No Known Activations