INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ك
    1.55
    1.52
    ש
    1.28
    তে
    1.26
     
    1.23
    ط
    1.22
    1.22
    هم
    1.21
    های
    1.20
    AM
    1.18
    POSITIVE LOGITS
    u
    1.59
    ués
    1.20
    ad
    1.15
    uah
    1.11
    i
    1.11
    ase
    1.09
    al
    1.09
    raient
    1.06
    te
    1.05
    cible
    1.05
    Act Density 0.009%

    No Known Activations