INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Bened
    -0.08
    คำ
    -0.06
     deney
    -0.06
     Rod
    -0.06
     происходит
    -0.06
     руки
    -0.06
     henne
    -0.06
     religion
    -0.06
     Lies
    -0.06
     هفت
    -0.06
    POSITIVE LOGITS
     ebook
    0.08
     Ebook
    0.08
     eBooks
    0.08
    Publish
    0.07
    spread
    0.07
    不存在
    0.07
    eur
    0.07
     confronted
    0.06
     affect
    0.06
     ebooks
    0.06
    Act Density 0.003%

    No Known Activations