INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    1.74
    ا
    1.64
    ع
    1.64
    1.57
    ना
    1.53
    да
    1.52
    ك
    1.50
    ة
    1.48
    1.48
    و
    1.45
    POSITIVE LOGITS
    }
    1.23
     
    1.16
    \
    1.16
     for
    1.10
    DB
    1.02
     enkel
    1.01
    RE
    0.99
     kom
    0.96
    LC
    0.96
    .
    0.96
    Act Density 0.000%

    No Known Activations