INDEX
Explanations
words related to brightness or shining
words that convey a sense of brightness or happiness
New Auto-Interp
Negative Logits
Blocks
-0.67
DOWN
-0.64
Stories
-0.61
ENTS
-0.60
Schools
-0.60
confir
-0.59
Glass
-0.59
rice
-0.59
rain
-0.58
adoption
-0.58
POSITIVE LOGITS
efully
1.81
eful
1.68
aming
1.43
amed
1.23
eking
1.22
ams
1.16
eping
0.98
istered
0.97
am
0.97
eks
0.95
Activations Density 0.044%