INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ۔
    0.60
    on
    0.55
    0.55
    0.54
    0.54
    0.52
    ।]
    0.49
    the
    0.47
    0.46
    گ
    0.46
    POSITIVE LOGITS
    ,
    0.52
    ä
    0.50
    ното
    0.45
    -
    0.45
    us
    0.44
    ية
    0.44
    0.43
    ing
    0.43
    IN
    0.42
    ih
    0.41
    Act Density 0.007%

    No Known Activations