INDEX
Explanations
various types of cuisines and food-related terms
New Auto-Interp
Negative Logits
akin
-0.16
iro
-0.15
ould
-0.15
odor
-0.14
inou
-0.14
enda
-0.14
ptions
-0.14
cases
-0.14
oupon
-0.14
olini
-0.14
POSITIVE LOGITS
style
0.40
-style
0.39
style
0.37
Style
0.33
_style
0.31
-inspired
0.30
styled
0.28
STYLE
0.28
Style
0.28
(style
0.26
Activations Density 0.100%