INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     sobie
    -0.09
    roong
    -0.08
     عوام
    -0.08
    afa
    -0.08
    غا
    -0.08
     ال
    -0.08
     Lamar
    -0.08
    ya
    -0.07
    ावर
    -0.07
     kopi
    -0.07
    POSITIVE LOGITS
    Warnings
    0.11
     warnings
    0.10
     WARNING
    0.09
     Warning
    0.09
    Warning
    0.09
    -unused
    0.08
     muster
    0.08
    _WARN
    0.08
    -warning
    0.08
    -devel
    0.08
    Act Density 0.000%

    No Known Activations