INDEX
Explanations
words related to the concept of 'Hug'
expressions of frustration or exclamation
New Auto-Interp
Negative Logits
washing
-0.68
afterlife
-0.66
bank
-0.65
cry
-0.65
wash
-0.65
shields
-0.64
immortal
-0.64
equilibrium
-0.64
dishes
-0.63
Chau
-0.61
POSITIVE LOGITS
UG
4.41
ugs
1.75
ug
1.70
BUG
1.57
UGH
1.52
UGE
1.43
UST
1.42
UB
1.35
ugg
1.31
UD
1.29
Activations Density 0.011%