INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    (unique
    -0.08
     Nk
    -0.08
    шілі
    -0.08
    dni
    -0.08
    -0.07
     Ethiopia
    -0.07
     ชั้น
    -0.07
    -0.07
    /views
    -0.07
     Kepala
    -0.07
    POSITIVE LOGITS
     richiesta
    0.10
    alai
    0.09
     banning
    0.08
     richi
    0.08
     requesting
    0.08
     banned
    0.08
     faim
    0.08
     zaht
    0.08
     reject
    0.08
     stringent
    0.08
    Act Density 0.010%

    No Known Activations