INDEX
    Explanations
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.07
    2:0.07
    3:0.07
    4:0.11
    5:0.06
    6:0.06
    7:0.18
    8:0.05
    9:0.06
    10:0.07
    11:0.08
    Negative Logits
     provisions
    -1.52
     rumors
    -1.46
     watering
    -1.43
     unwelcome
    -1.38
     overt
    -1.37
     hostilities
    -1.37
     quarters
    -1.35
     naming
    -1.34
     rumours
    -1.34
     perjury
    -1.33
    POSITIVE LOGITS
    erity
    1.73
    rimp
    1.70
    maxwell
    1.66
    romy
    1.60
    ーティ
    1.59
    ancers
    1.59
    itars
    1.56
    icum
    1.56
    fman
    1.55
    osponsors
    1.53
    Act Density 0.000%

    No Known Activations