INDEX
Explanations
items related to the sun
mentions of the sun
New Auto-Interp
Negative Logits
osures
-0.72
ij士
-0.70
ourgeois
-0.70
Cosponsors
-0.69
razil
-0.69
ĵĺ
-0.69
ollow
-0.69
UGE
-0.69
ername
-0.69
ilage
-0.67
POSITIVE LOGITS
flower
1.15
lit
1.10
shine
1.09
beam
1.08
rays
1.03
burst
1.02
spot
1.01
nah
1.01
burn
0.99
bat
0.96
Activations Density 0.018%