INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     지정
    -0.06
     jan
    -0.06
     Wie
    -0.06
     cif
    -0.06
     Ko
    -0.06
     Üst
    -0.06
     taille
    -0.06
    vertiser
    -0.06
    ivia
    -0.06
    ’an
    -0.06
    POSITIVE LOGITS
     glorious
    0.32
    orious
    0.15
    ondrous
    0.09
    Virgin
    0.08
     marital
    0.07
    _unique
    0.07
     Shooting
    0.07
     UIAlert
    0.07
     Rox
    0.07
     miraculous
    0.07
    Act Density 0.001%

    No Known Activations