INDEX
    Explanations
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.21
    3:0.25
    4:0.15
    5:0.02
    6:0.03
    7:0.04
    8:0.10
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
    -+-+
    -1.48
    ojure
    -1.35
    atism
    -1.32
    "))
    -1.28
     underestimated
    -1.28
     besides
    -1.25
    rel
    -1.25
    thanks
    -1.24
    atile
    -1.23
     somehow
    -1.23
    POSITIVE LOGITS
     appell
    1.46
     adject
    1.30
     guiActive
    1.28
    igible
    1.27
     hall
    1.24
     euphem
    1.24
     persuasion
    1.23
     creditor
    1.23
    1.22
    =#
    1.22
    Act Density 0.176%

    No Known Activations