INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Admir
    -0.08
    -0.08
     wounds
    -0.08
     pall
    -0.08
     amput
    -0.07
     Cad
    -0.07
     Alison
    -0.07
     PROP
    -0.07
    BD
    -0.07
    -0.07
    POSITIVE LOGITS
     Ph
    0.08
     dioxide
    0.08
    Far
    0.08
     carbide
    0.08
     Hir
    0.08
    កម្ម
    0.07
     Liu
    0.07
     FIR
    0.07
     Buck
    0.07
    atra
    0.07
    Act Density 0.006%

    No Known Activations