INDEX
Explanations
words related to temperature, especially referencing hot and cold sensations
New Auto-Interp
Negative Logits
vil
-0.15
naire
-0.15
eer
-0.15
naires
-0.15
LESS
-0.15
ìķ¼
-0.14
sthrough
-0.14
alist
-0.14
.bunifuFlatButton
-0.14
luv
-0.14
POSITIVE LOGITS
ness
0.31
(er
0.23
ening
0.21
NESS
0.20
à¹Ĩ
0.19
à¹Ĩ
0.19
ly
0.18
ened
0.18
nes
0.17
enough
0.17
Activations Density 0.154%