INDEX
    Explanations

    category or uminescence

    New Auto-Interp
    Negative Logits
    cibles
    -0.59
    }';
    -0.55
    rent
    -0.54
    ValueStyle
    -0.54
     typhoon
    -0.54
     gradova
    -0.54
    avía
    -0.53
    cipar
    -0.52
     متعلقه
    -0.52
    UNI
    -0.51
    POSITIVE LOGITS
     fumée
    0.73
     automatiques
    0.72
     sapore
    0.69
     copertura
    0.65
     carriera
    0.64
     aveug
    0.61
     spoluprá
    0.61
     marrone
    0.61
     mères
    0.60
     våre
    0.59
    Act Density 0.222%

    No Known Activations