INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     sleeve
    -0.08
    edition
    -0.08
     basal
    -0.08
    Edition
    -0.07
     pand
    -0.07
     exhibition
    -0.07
     excerpt
    -0.07
     braided
    -0.07
     plast
    -0.07
    ater
    -0.07
    POSITIVE LOGITS
     capacit
    0.09
    discover
    0.09
     Lauf
    0.08
     Grund
    0.08
    _FINE
    0.08
     INV
    0.08
     చిర
    0.07
     Yan
    0.07
    Kenzie
    0.07
    -служ
    0.07
    Act Density 0.002%

    No Known Activations