INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    tem
    -0.09
     Nate
    -0.08
     nahe
    -0.08
     leaps
    -0.08
    Tony
    -0.07
    AGR
    -0.07
     Lamb
    -0.07
    Host
    -0.07
    enswert
    -0.07
    upar
    -0.07
    POSITIVE LOGITS
     alike
    0.08
    _given
    0.07
     rigid
    0.07
     promedio
    0.07
     deg
    0.07
    Totals
    0.07
    0.07
     regio
    0.07
    0.07
    ایک
    0.07
    Act Density 0.005%

    No Known Activations