INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    afil
    -0.07
     budou
    -0.07
     Blu
    -0.07
     recording
    -0.06
     recorded
    -0.06
    busters
    -0.06
    -0.06
    DCF
    -0.06
     sanitized
    -0.06
     abaixo
    -0.06
    POSITIVE LOGITS
     Pinterest
    0.15
    Pinterest
    0.12
     pinterest
    0.08
    unce
    0.07
     кас
    0.07
    ']);
    0.07
    .pool
    0.06
    (Point
    0.06
     linspace
    0.06
    hung
    0.06
    Act Density 0.001%

    No Known Activations