INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Lazar
    -0.07
    ClassLoader
    -0.07
     Amber
    -0.06
     obr
    -0.06
     málo
    -0.06
    -0.06
    -0.06
    -0.06
     اسلامی
    -0.06
    bre
    -0.06
    POSITIVE LOGITS
     point
    0.20
     Point
    0.19
    Point
    0.19
     points
    0.17
    point
    0.17
     POINT
    0.16
    -point
    0.15
     Points
    0.14
    _point
    0.13
    _points
    0.13
    Act Density 0.053%

    No Known Activations