INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     thôi
    -0.39
     publicly
    -0.39
     associations
    -0.39
     privately
    -0.39
    Friends
    -0.38
    -0.38
    вля
    -0.37
     pribadi
    -0.36
    ระ
    -0.35
     association
    -0.35
    POSITIVE LOGITS
    Personensuche
    0.66
     news
    0.64
     disambiguazione
    0.63
     للاسماء
    0.57
     headlines
    0.56
     الحره
    0.56
    Portail
    0.54
     queſta
    0.54
    лтемелер
    0.54
     News
    0.53
    Act Density 0.263%

    No Known Activations