INDEX
    Explanations

    non-English text

    New Auto-Interp
    Negative Logits
    ٌ
    -0.09
     Hoff
    -0.08
     Für
    -0.08
    603
    -0.08
    -0.08
     Mendoza
    -0.08
    อกจาก
    -0.07
    ließlich
    -0.07
    lah
    -0.07
    (regex
    -0.07
    POSITIVE LOGITS
     courrier
    0.10
     workplace
    0.09
     credito
    0.08
     enlightenment
    0.08
     وطن
    0.08
     pesca
    0.08
     remembrance
    0.08
     village
    0.08
    едиа
    0.08
    chir
    0.08
    Act Density 0.102%

    No Known Activations