INDEX
Explanations
instances of the word "Sun" with varying suffixes or contexts
mentions of the word "Sun."
New Auto-Interp
Negative Logits
ngth
-0.94
ussen
-0.76
razil
-0.75
ersive
-0.73
ucha
-0.73
captcha
-0.72
izabeth
-0.71
Hodg
-0.71
axter
-0.68
emetery
-0.65
POSITIVE LOGITS
shine
1.04
light
0.95
nah
0.90
Sun
0.90
rays
0.87
lit
0.87
ray
0.86
beam
0.86
burn
0.85
flower
0.84
Activations Density 0.009%