INDEX
Explanations
words related to spicy foods or flavors
phrases that convey excitement about food and social experiences
New Auto-Interp
Negative Logits
entity
-0.69
[+
-0.63
ourses
-0.62
Therefore
-0.60
rans
-0.60
struct
-0.58
ructure
-0.58
mediation
-0.58
Struct
-0.57
Internal
-0.56
POSITIVE LOGITS
badass
0.78
booze
0.77
snack
0.76
grandma
0.75
geek
0.74
nerd
0.74
vape
0.74
coolest
0.73
;)
0.72
fancy
0.72
Activations Density 1.597%