INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     swiper
    -0.08
     Lessons
    -0.08
    utely
    -0.08
    Lessons
    -0.08
     llamado
    -0.07
     donné
    -0.07
     haver
    -0.07
     pamię
    -0.07
     pengh
    -0.07
     schnelle
    -0.07
    POSITIVE LOGITS
    	On
    0.08
    ituksen
    0.08
    Pi
    0.08
    misc
    0.07
    _about
    0.07
    _on
    0.07
     Misc
    0.07
    _ON
    0.07
    _contents
    0.07
     emitted
    0.07
    Act Density 0.005%

    No Known Activations