INDEX
    Explanations

    foreign languages

    New Auto-Interp
    Negative Logits
     frequentemente
    -0.08
     rag
    -0.08
     indicative
    -0.08
     renowned
    -0.08
     कन
    -0.07
    -0.07
    -0.07
     emblem
    -0.07
    (element
    -0.07
    ardu
    -0.07
    POSITIVE LOGITS
     afirma
    0.08
     хозя
    0.08
    between
    0.08
     ترکی
    0.07
     Good
    0.07
     Honors
    0.07
     Нет
    0.07
     téh
    0.07
    wartz
    0.07
    wrap
    0.07
    Act Density 0.000%

    No Known Activations