INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     paw
    -0.09
    -0.09
    /result
    -0.08
     kry
    -0.08
    paw
    -0.08
     tsakan
    -0.07
     Spielberg
    -0.07
     Lightroom
    -0.07
     себе
    -0.07
     znam
    -0.07
    POSITIVE LOGITS
     ibn
    0.09
     رضي
    0.09
     conquest
    0.09
     Burial
    0.08
     صلى
    0.08
     baptism
    0.08
     evangel
    0.08
     Expansion
    0.08
     Loader
    0.08
     posteriores
    0.08
    Act Density 0.006%

    No Known Activations