INDEX
    Explanations

    comparisons and quantities

    New Auto-Interp
    Negative Logits
     silhouette
    -0.07
     voyeur
    -0.06
    nosis
    -0.06
    prior
    -0.06
     clips
    -0.06
     tex
    -0.06
    captcha
    -0.06
    irical
    -0.06
    	Simple
    -0.06
     irony
    -0.06
    POSITIVE LOGITS
    -short
    0.07
    _FILTER
    0.07
    _filter
    0.06
    .Parameter
    0.06
    0.06
    ategorical
    0.06
     indicate
    0.06
    Paused
    0.06
    .getSelected
    0.06
     Neg
    0.06
    Act Density 0.164%

    No Known Activations