INDEX
    Explanations

    ordinal numbers

    New Auto-Interp
    Negative Logits
     Il
    -0.08
    _components
    -0.08
     שח
    -0.08
    Il
    -0.08
    Components
    -0.07
    opin
    -0.07
    נס
    -0.07
     organiz
    -0.07
     inhabitants
    -0.07
    -0.07
    POSITIVE LOGITS
     tampoco
    0.08
     affidavit
    0.08
     notified
    0.08
    irà
    0.08
    	hide
    0.08
     dirigir
    0.08
    ;/
    0.07
    .up
    0.07
     shader
    0.07
    ;width
    0.07
    Act Density 0.000%

    No Known Activations