INDEX
    Explanations
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.07
    2:0.08
    3:0.08
    4:0.09
    5:0.08
    6:0.08
    7:0.07
    8:0.07
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
    ewitness
    -3.14
    itored
    -3.02
     Drink
    -2.83
    hof
    -2.76
     dispensary
    -2.70
    -2.70
    ��
    -2.70
     Taxi
    -2.66
    arijuana
    -2.66
    ribes
    -2.63
    POSITIVE LOGITS
     Neon
    2.64
     decay
    2.63
     resh
    2.59
     neut
    2.52
     coats
    2.44
    fires
    2.44
     kittens
    2.43
     decom
    2.43
     declass
    2.42
     Penguin
    2.38
    Act Density 0.000%

    No Known Activations