INDEX
    Explanations
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.08
    4:0.07
    5:0.09
    6:0.08
    7:0.07
    8:0.08
    9:0.07
    10:0.08
    11:0.09
    Negative Logits
    ause
    -2.99
    OTUS
    -2.87
    umenthal
    -2.75
    qual
    -2.73
    icates
    -2.53
    urations
    -2.50
    redo
    -2.48
     regrets
    -2.48
    icate
    -2.45
    cca
    -2.42
    POSITIVE LOGITS
     Gang
    3.44
     Robot
    3.25
     Shi
    2.89
     Shin
    2.88
     Murd
    2.85
     Tor
    2.74
     Kid
    2.73
    Rob
    2.71
     Shank
    2.71
     gang
    2.70
    Act Density 0.000%

    No Known Activations