INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Lifestyle
    -0.08
    Formatting
    -0.08
    Oil
    -0.08
     Lifestyle
    -0.08
     Դուք
    -0.07
    DED
    -0.07
     Jerusalem
    -0.07
     unre
    -0.07
    _growth
    -0.07
     مضمون
    -0.07
    POSITIVE LOGITS
     largeur
    0.09
     slices
    0.09
    altura
    0.09
     widths
    0.09
    0.09
    -wise
    0.08
    aturi
    0.08
     narrower
    0.08
    isio
    0.08
     tallest
    0.08
    Act Density 0.023%

    No Known Activations