INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ي
    1.55
    يلي
    1.33
    ين
    1.17
    vať
    1.13
     empêcher
    1.12
    ת
    1.10
    يت
    1.09
    Aslamualaikum
    1.09
    تي
    1.08
    ból
    1.08
    POSITIVE LOGITS
     I
    1.38
     to
    1.23
     It
    1.20
     l
    1.14
    1.09
     U
    1.06
     for
    1.05
     by
    1.05
     By
    1.05
     T
    1.04
    Act Density 0.000%

    No Known Activations