INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    شاه
    -0.06
     Patron
    -0.06
     phổ
    -0.06
     maintenant
    -0.06
     буде
    -0.06
     visc
    -0.06
    Ted
    -0.06
     Suff
    -0.06
     outpatient
    -0.06
    ungi
    -0.06
    POSITIVE LOGITS
    xia
    0.11
     Congo
    0.11
     Gaga
    0.08
    via
    0.06
    Mock
    0.06
     dp
    0.06
     traders
    0.06
    _self
    0.06
     Getter
    0.06
    .erb
    0.06
    Act Density 0.003%

    No Known Activations