INDEX
Explanations
mentions of specific HP product models and categories
New Auto-Interp
Negative Logits
igel
-0.16
梯
-0.16
hab
-0.15
.dirty
-0.15
ergency
-0.15
lectric
-0.15
yor
-0.14
obus
-0.14
emma
-0.14
atables
-0.14
POSITIVE LOGITS
HP
0.40
HP
0.36
Hew
0.34
hp
0.31
Hp
0.30
.hp
0.29
Hp
0.28
_HP
0.27
hp
0.26
_hp
0.23
Activations Density 0.005%