INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    1.11
    که
    1.07
    mr
    1.07
    т
    1.05
    ک
    1.05
    ב
    1.02
    на
    0.98
    0.97
    اک
    0.96
    کو
    0.96
    POSITIVE LOGITS
    )
    1.09
    {
    1.09
    ٩
    1.06
     a
    1.04
     erfol
    0.96
    f
    0.94
    ו
    0.93
     rapidly
    0.91
    }
    0.88
    UR
    0.87
    Act Density 0.013%

    No Known Activations