INDEX
Explanations
proper nouns and names
names of individuals, particularly those associated with entertainment or sports
New Auto-Interp
Negative Logits
³³³
-0.79
izont
-0.78
RON
-0.76
acists
-0.74
acles
-0.74
acies
-0.73
Irish
-0.72
acle
-0.72
riors
-0.71
urtle
-0.71
POSITIVE LOGITS
Gomez
1.46
omez
0.86
enstein
0.84
mustache
0.74
Canaver
0.74
Jarvis
0.73
Swap
0.68
hairc
0.67
esi
0.66
Emin
0.66
Activations Density 0.014%