INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    p
    1.29
    o
    1.22
    in
    1.13
    1.13
    c
    1.12
    m
    1.06
    م
    1.05
    n
    1.03
    r
    1.02
    en
    0.98
    POSITIVE LOGITS
     ﺍﻟ
    0.98
    0.95
    0.86
    SOUND
    0.84
    0.82
     μην
    0.81
    0.80
    0.79
    siniz
    0.79
    0.79
    Act Density 0.434%

    No Known Activations