INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     dissatisf
    0.43
     صح
    0.41
     scala
    0.40
     partant
    0.39
     عليه
    0.39
     devast
    0.38
     Frege
    0.38
     wages
    0.38
     wildfires
    0.38
     mää
    0.38
    POSITIVE LOGITS
     rounded
    1.88
     corners
    1.88
    Rounded
    1.80
     Rounded
    1.74
     corner
    1.70
     rounding
    1.69
    corners
    1.66
    Corner
    1.66
    rounded
    1.62
     Corners
    1.60
    Act Density 0.016%

    No Known Activations