INDEX
    Explanations

    Portuguese language

    New Auto-Interp
    Negative Logits
     of
    -0.10
     OF
    -0.08
    P
    -0.07
     Of
    -0.07
    of
    -0.07
    _of
    -0.07
    _c
    -0.07
    h
    -0.06
     ':
    -0.06
    -0.06
    POSITIVE LOGITS
     pela
    0.10
     zum
    0.09
     pelos
    0.09
     au
    0.09
     dalla
    0.09
     nel
    0.09
     وال
    0.08
     nella
    0.08
     zur
    0.08
     aux
    0.08
    Act Density 0.066%

    No Known Activations