INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ögen
    -0.08
     nač
    -0.07
    steller
    -0.07
     Kul
    -0.07
     ɗ
    -0.07
     viability
    -0.07
     wpły
    -0.07
     ceil
    -0.07
    -0.07
    Coord
    -0.07
    POSITIVE LOGITS
     betrayal
    0.11
     insiders
    0.11
     %[
    0.09
     Trusted
    0.09
     betrayed
    0.09
     trusted
    0.08
     betray
    0.08
     내부
    0.08
     %@",
    0.08
     সমস্যা
    0.08
    Act Density 0.047%

    No Known Activations