INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     eighty
    1.08
     Nine
    1.05
     ninth
    1.03
     eight
    0.98
     nine
    0.98
     Eighty
    0.97
     ninety
    0.96
     eighth
    0.95
     Ninth
    0.91
    0.91
    POSITIVE LOGITS
    4
    1.82
    1.51
    ۴
    1.39
     ۴
    1.33
    ٤
    1.28
    1.25
     four
    1.25
    3
    1.23
    1.22
    1.21
    Act Density 0.224%

    No Known Activations