INDEX
    Explanations

    French language

    New Auto-Interp
    Negative Logits
    freq
    -0.09
     freq
    -0.09
    ICP
    -0.09
    юць
    -0.09
    .freq
    -0.09
    Export
    -0.08
    -frequency
    -0.08
     thor
    -0.08
     medizin
    -0.08
    _freq
    -0.08
    POSITIVE LOGITS
     staging
    0.08
     distinct
    0.07
     вовсе
    0.07
     aggiorn
    0.07
     где
    0.07
    0.07
     Nord
    0.06
     ndry
    0.06
    ская
    0.06
    ાવો
    0.06
    Act Density 0.000%

    No Known Activations