INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     palp
    -0.08
     spa
    -0.08
     ஒன்ற
    -0.08
     webpack
    -0.08
     이동
    -0.08
    spa
    -0.08
     ഏറ്റ
    -0.08
    Spa
    -0.08
    -0.07
     اللو
    -0.07
    POSITIVE LOGITS
     persistent
    0.09
     perennial
    0.09
     Persistent
    0.08
    persistent
    0.08
    nea
    0.08
     સતત
    0.08
    бирать
    0.08
    ucun
    0.08
     cough
    0.08
     sürekli
    0.08
    Act Density 0.002%

    No Known Activations