INDEX
Explanations
mentions and various forms of garlic in food-related contexts
New Auto-Interp
Negative Logits
ibia
-0.16
onica
-0.15
Dalton
-0.15
DM
-0.15
etting
-0.14
_DM
-0.13
ego
-0.13
room
-0.13
hu
-0.13
à¥Ĥ
-0.13
POSITIVE LOGITS
urdy
0.17
æķ
0.15
/her
0.15
iglia
0.15
emma
0.14
iform
0.14
Busy
0.14
udent
0.14
utow
0.14
ocy
0.14
Activations Density 0.005%