INDEX
Explanations
references to financial transactions and obligations
New Auto-Interp
Negative Logits
cht
-0.19
repay
-0.18
payment
-0.18
payout
-0.17
payouts
-0.17
repayment
-0.17
payments
-0.16
payment
-0.16
Spending
-0.16
payments
-0.16
POSITIVE LOGITS
attention
0.29
back
0.24
lip
0.23
homage
0.23
Attention
0.23
tribute
0.22
checks
0.22
attention
0.21
rolls
0.21
off
0.21
Activations Density 0.056%