INDEX
Explanations
proper nouns or pronouns referring to a specific person
occurrences of a specific individual's name or pronouns
New Auto-Interp
Negative Logits
Columb
-0.69
Veter
-0.62
Kali
-0.61
Collective
-0.61
Blazing
-0.61
earch
-0.61
Gems
-0.60
Nightmares
-0.60
Bella
-0.59
Girls
-0.59
POSITIVE LOGITS
zbollah
1.38
'll
1.17
eded
1.08
campaigned
1.08
'd
1.07
appoint
0.98
tweeted
0.97
've
0.95
enegger
0.93
pard
0.91
Activations Density 0.243%