INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Ι
    1.25
    1.02
    Đ
    1.01
    İ
    0.98
    شی
    0.97
    Jika
    0.95
    Z
    0.95
    نی
    0.93
    0.93
    کت
    0.91
    POSITIVE LOGITS
    -
    1.20
    at
    1.05
    р
    1.02
    ↵↵
    1.01
    a
    0.96
    с
    0.91
    0.91
    в
    0.89
    0.84
    ма
    0.82
    Act Density 0.155%

    No Known Activations