INDEX
    Explanations
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.07
    3:0.08
    4:0.09
    5:0.08
    6:0.08
    7:0.09
    8:0.08
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     Shea
    -2.61
     OEM
    -2.31
     ancest
    -2.25
     CES
    -2.22
     IEEE
    -2.18
     FedEx
    -2.06
     Pf
    -1.97
     Lowell
    -1.96
     Omni
    -1.95
     Osw
    -1.91
    POSITIVE LOGITS
     brut
    2.40
    2.10
     fracturing
    2.07
     sacked
    2.05
     bruised
    2.05
     bruising
    2.04
    ahime
    1.97
    merce
    1.97
    igun
    1.97
    gebra
    1.95
    Act Density 0.000%

    No Known Activations