INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bmp
    -0.07
     یون
    -0.07
    Un
    -0.07
    lingen
    -0.06
    -0.06
    ophobic
    -0.06
    _cv
    -0.06
    bero
    -0.06
    _Pr
    -0.06
    ọt
    -0.06
    POSITIVE LOGITS
    _mac
    0.08
    _MAC
    0.08
     Mac
    0.07
     afflicted
    0.07
    ?>
    0.07
    Mac
    0.06
    .pan
    0.06
     critics
    0.06
     associate
    0.06
    DEFAULT
    0.06
    Act Density 0.006%

    No Known Activations