INDEX
    Explanations

    S, E leading ". S light

    New Auto-Interp
    Negative Logits
    the
    0.46
    an
    0.45
    ap
    0.41
    ad
    0.41
    ان
    0.41
    0.38
    this
    0.36
    n
    0.35
    на
    0.35
    ch
    0.34
    POSITIVE LOGITS
     ٣
    0.25
     I
    0.24
    \
    0.24
    -
    0.23
    (
    0.23
     sullen
    0.23
    :");
    0.23
     como
    0.22
     pessoa
    0.22
    )=\
    0.22
    Act Density 0.051%

    No Known Activations