INDEX
Explanations
words related to borrowing and financial transactions.
New Auto-Interp
Negative Logits
Santa
-0.08
Ult
-0.08
IDs
-0.07
Stars
-0.07
show
-0.07
ulent
-0.07
explode
-0.07
excellence
-0.07
plaza
-0.07
Plaza
-0.07
POSITIVE LOGITS
borrow
0.10
borrower
0.10
borrow
0.09
.borrow
0.09
Borrow
0.09
borrowers
0.09
borrowing
0.08
ろう
0.08
resh
0.07
borough
0.07
Activations Density 0.003%