INDEX
    Explanations
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.02
    2:0.04
    3:0.32
    4:0.03
    5:0.11
    6:0.02
    7:0.05
    8:0.05
    9:0.02
    10:0.12
    11:0.03
    Negative Logits
    bart
    -1.97
     Malf
    -1.90
     interviewer
    -1.88
    Assistant
    -1.88
    iltration
    -1.86
     cleanup
    -1.82
    Discussion
    -1.81
     Allison
    -1.80
     rehearsal
    -1.79
     Painter
    -1.78
    POSITIVE LOGITS
     currencies
    3.70
    coins
    3.55
     coins
    3.29
     currency
    3.22
     fiat
    3.15
     Bitcoins
    2.98
     tokens
    2.90
     bitcoins
    2.88
     cryptocurrencies
    2.86
     cryptocurrency
    2.84
    Act Density 0.309%

    No Known Activations