INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     sessões
    -0.08
    -ft
    -0.08
     bloc
    -0.08
    .blit
    -0.08
     obsess
    -0.07
    _enemy
    -0.07
    -note
    -0.07
     Igor
    -0.07
     admirer
    -0.07
     aeron
    -0.07
    POSITIVE LOGITS
    .allow
    0.11
    .Nullable
    0.11
     Nullable
    0.11
    nullable
    0.10
    Nullable
    0.10
    _nullable
    0.10
     nullable
    0.10
     permiss
    0.10
     facult
    0.09
    允许
    0.09
    Act Density 0.004%

    No Known Activations