INDEX
Explanations
mentions of a specific entity named "Sun"
occurrences of the word "Sun" in various contexts
New Auto-Interp
Negative Logits
ngth
-1.01
ussen
-0.78
izabeth
-0.70
captcha
-0.69
FINE
-0.66
Hodg
-0.65
leneck
-0.65
ourgeois
-0.64
axter
-0.64
OHN
-0.64
POSITIVE LOGITS
shine
1.08
beam
1.05
burst
1.01
flower
1.00
ning
0.96
light
0.95
nah
0.91
belt
0.90
bow
0.89
lit
0.89
Activations Density 0.011%