INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    _
    1.45
    f
    1.42
    s
    1.27
    in
    1.10
    0
    1.02
    ,
    0.93
    fice
    0.93
    tti
    0.92
    hren
    0.91
    <0x80>
    0.88
    POSITIVE LOGITS
    1.28
    ב
    1.23
    ب
    1.13
    1.09
    Μ
    1.07
    1.06
    ون
    1.02
    Г
    1.02
    1.02
    1.01
    Act Density 0.003%

    No Known Activations