INDEX
    Explanations

    foreign or non-standard language

    New Auto-Interp
    Negative Logits
    Notre
    0.47
    ഡിയോ
    0.46
    犯罪
    0.45
    environmental
    0.44
    Designs
    0.44
    াস
    0.43
     Notre
    0.42
    സ്‌
    0.42
     wetting
    0.42
    dental
    0.42
    POSITIVE LOGITS
     असामान्य
    0.43
     maliciously
    0.43
    我不
    0.42
     Abb
    0.42
    ümü
    0.42
     Overton
    0.42
     xem
    0.42
    ubis
    0.42
     alguma
    0.41
    rezz
    0.41
    Act Density 0.006%

    No Known Activations