INDEX
Explanations
last names of people
names of individuals or entities
New Auto-Interp
Negative Logits
CLS
-0.65
distinctions
-0.64
overlap
-0.64
Glac
-0.60
divisions
-0.58
\(\
-0.58
wider
-0.57
broader
-0.56
wcs
-0.56
qual
-0.55
POSITIVE LOGITS
Sr
0.98
Jr
0.97
ovich
0.90
kowski
0.90
sson
0.89
udeau
0.86
iewicz
0.82
ardi
0.82
orst
0.81
III
0.78
Activations Density 0.200%