INDEX
Explanations
proper nouns or names, particularly the name "Bill"
the name "Bill" in various contexts
New Auto-Interp
Negative Logits
srf
-0.86
exha
-0.77
detain
-0.74
referen
-0.74
lightsaber
-0.73
cffff
-0.72
ingred
-0.72
glim
-0.71
conservancy
-0.71
veter
-0.70
POSITIVE LOGITS
iard
1.28
Maher
1.13
Cosby
1.08
ingham
1.05
Belichick
0.95
ington
0.94
ions
0.94
iton
0.89
Gates
0.87
Hicks
0.85
Activations Density 0.014%