INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.09
    3:0.07
    4:0.10
    5:0.09
    6:0.09
    7:0.08
    8:0.06
    9:0.07
    10:0.07
    11:0.08
    Negative Logits
    loss
    -3.10
    idepress
    -3.10
    doms
    -3.02
    anza
    -3.01
    netflix
    -2.91
     Moff
    -2.86
    edom
    -2.84
    Fail
    -2.79
     Poe
    -2.78
    Kill
    -2.77
    POSITIVE LOGITS
     ingred
    3.34
    Catalog
    3.07
     Creation
    2.97
    ********************************
    2.92
     paperwork
    2.82
     bou
    2.76
     conserv
    2.71
     loader
    2.68
     Construction
    2.67
    Construction
    2.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.