INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     société
    -0.07
    ý
    -0.07
     NEWS
    -0.07
     nations
    -0.06
    616
    -0.06
     characterization
    -0.06
     Institutions
    -0.06
     الرسم
    -0.06
     institutions
    -0.06
     Preference
    -0.06
    POSITIVE LOGITS
     становить
    0.06
     Def
    0.06
    licative
    0.06
    _Arg
    0.06
    ernals
    0.06
     تح
    0.06
     RIP
    0.06
    Budget
    0.06
    _seg
    0.06
     concl
    0.06
    Act Density 0.029%

    No Known Activations