INDEX
    Explanations

    substituted

    New Auto-Interp
    Negative Logits
     alunos
    -0.08
    FFFFFF
    -0.07
    _TRANSFER
    -0.07
     Giovanni
    -0.07
    cls
    -0.06
     گاه
    -0.06
    -0.06
    نين
    -0.06
     Warriors
    -0.06
     آذ
    -0.06
    POSITIVE LOGITS
     overdose
    0.07
     dread
    0.06
    ระเบ
    0.06
     uplift
    0.06
     TM
    0.06
    accept
    0.06
    олог
    0.06
     reliably
    0.06
     fundraiser
    0.06
     prosecution
    0.06
    Act Density 0.003%

    No Known Activations