INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    u
    0.41
    ad
    0.41
     of
    0.39
    to
    0.37
     werd
    0.37
    is
    0.35
     to
    0.35
    á
    0.35
    uft
    0.35
    um
    0.34
    POSITIVE LOGITS
    Ы
    0.29
    N
    0.28
    Y
    0.28
    Ink
    0.26
    0.25
     Castile
    0.25
    .
    0.23
    -
    0.23
    U
    0.23
     Gotham
    0.23
    Act Density 0.055%

    No Known Activations