INDEX
Explanations
items related to cooking and food preparation
New Auto-Interp
Negative Logits
Feld
-0.16
_slope
-0.16
289
-0.15
uga
-0.14
idis
-0.14
Bez
-0.14
509
-0.14
Slo
-0.14
plat
-0.14
_INTR
-0.13
POSITIVE LOGITS
stick
1.60
Stick
1.52
sticks
1.43
stick
1.41
Stick
1.40
sticking
1.21
sticks
1.16
stuck
1.07
sticky
0.91
sticky
0.85
Activations Density 0.234%