INDEX
    Explanations
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.07
    3:0.08
    4:0.10
    5:0.08
    6:0.08
    7:0.09
    8:0.07
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
     terminating
    -2.07
     stabilization
    -2.02
    dylib
    -2.02
     pavement
    -1.99
     Motion
    -1.98
     grinding
    -1.96
     banners
    -1.93
    ?,
    -1.91
     ultrasound
    -1.90
     foam
    -1.89
    POSITIVE LOGITS
     answ
    2.40
     empath
    2.26
    anie
    2.25
    inces
    2.22
    arag
    2.20
    ongyang
    2.17
    ago
    2.17
     knows
    2.14
    viron
    2.13
    enez
    2.13
    Act Density 0.000%

    No Known Activations