INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    _mag
    -0.09
     Mauro
    -0.08
    EAR
    -0.08
    (CG
    -0.08
    yness
    -0.08
     EAR
    -0.08
    232
    -0.08
    .prevent
    -0.08
    Integr
    -0.07
    (vec
    -0.07
    POSITIVE LOGITS
     pás
    0.08
     emocional
    0.08
     પટ
    0.08
    endedor
    0.08
     linens
    0.08
     datasets
    0.08
     suporte
    0.08
     bata
    0.08
     lady
    0.08
     sentimental
    0.07
    Act Density 0.000%

    No Known Activations