INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    و
    1.41
    o
    1.31
    i
    1.27
    1.26
    1.21
    ل
    1.19
    to
    1.16
    não
    1.15
    да
    1.09
    ta
    1.05
    POSITIVE LOGITS
    '
    1.59
    ים
    0.97
    (
    0.97
    ри
    0.95
     apothecary
    0.92
    adır
    0.91
    রা
    0.91
     universo
    0.91
    рила
    0.90
    .
    0.90
    Act Density 0.010%

    No Known Activations