INDEX
Explanations
phrases related to spending money
references to spending large amounts of money
New Auto-Interp
Negative Logits
ells
-0.73
oor
-0.68
hail
-0.63
dL
-0.63
major
-0.61
sup
-0.61
WIND
-0.61
Klu
-0.59
dismissal
-0.59
fun
-0.57
POSITIVE LOGITS
wisely
0.97
frivol
0.85
dollars
0.84
bucks
0.83
ibal
0.71
(£
0.70
ocating
0.69
unnecessarily
0.68
scarce
0.68
USD
0.67
Activations Density 0.105%