INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     fright
    -0.68
     antiv
    -0.68
     dressing
    -0.66
     improv
    -0.66
     au
    -0.65
     hon
    -0.65
    ierrez
    -0.63
     pause
    -0.61
     skim
    -0.60
     proport
    -0.60
    POSITIVE LOGITS
    sided
    1.07
    cv
    1.05
    =-=-=-=-=-=-=-=-
    1.03
    05
    1.02
    20439
    1.02
    Sep
    0.99
    eyed
    0.98
    Hour
    0.98
    2018
    0.97
    themed
    0.97
    Act Density 0.098%

    No Known Activations