INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     plein
    -0.08
     wines
    -0.08
     loc
    -0.08
     spl
    -0.08
    wine
    -0.07
     gepf
    -0.07
     Weiterbildung
    -0.07
     Spl
    -0.07
     Bever
    -0.07
     pois
    -0.07
    POSITIVE LOGITS
     cheek
    0.09
     المسلحة
    0.08
    UNCH
    0.08
    row
    0.08
    .row
    0.08
     Gaza
    0.08
    0.08
     Belfast
    0.08
     mechan
    0.08
     عرب
    0.07
    Act Density 0.010%

    No Known Activations