INDEX
Explanations
phrases related to the sun
repeated references to "Sun" in various contexts
New Auto-Interp
Negative Logits
ngth
-0.96
ussen
-0.84
razil
-0.75
ourgeois
-0.72
OHN
-0.70
izabeth
-0.69
avorite
-0.69
ucha
-0.69
captcha
-0.69
leneck
-0.67
POSITIVE LOGITS
shine
1.15
beam
0.96
light
0.96
lit
0.93
nah
0.93
flower
0.92
rise
0.90
burst
0.89
DAY
0.89
rays
0.87
Activations Density 0.009%