INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     certified
    -0.09
    adur
    -0.08
    _cert
    -0.08
     revend
    -0.08
     Cert
    -0.08
     quorum
    -0.08
     ICC
    -0.08
     Nit
    -0.07
    winning
    -0.07
    ierto
    -0.07
    POSITIVE LOGITS
    /widget
    0.08
     decad
    0.08
     dita
    0.07
     airy
    0.07
     decoration
    0.07
    *x
    0.07
     kena
    0.07
     öð
    0.07
     skrive
    0.07
     istifad
    0.07
    Act Density 0.015%

    No Known Activations