INDEX
Explanations
adjectives relating to facial features or expressions
phrases containing the word "faced" in various contexts
New Auto-Interp
Negative Logits
emo
-0.78
Recommended
-0.68
irl
-0.66
ODE
-0.65
LAN
-0.65
tnc
-0.65
dule
-0.65
fun
-0.65
imus
-0.64
ool
-0.63
POSITIVE LOGITS
faced
4.43
faces
1.08
haired
1.00
stained
0.97
facing
0.96
eyed
0.88
face
0.87
skinned
0.85
footed
0.84
stains
0.83
Activations Density 0.025%