INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ي
    1.48
    1.45
    y
    1.42
    ا
    1.41
    1.39
    ت
    1.32
    j
    1.18
    asch
    1.10
    ينا
    1.10
    tól
    1.10
    POSITIVE LOGITS
    .
    1.08
     się
    1.04
    ?
    0.94
     streets
    0.92
     driveway
    0.92
     worden
    0.91
     Hause
    0.91
     workday
    0.91
     recklessly
    0.91
     Meets
    0.89
    Act Density 0.223%

    No Known Activations