INDEX
Explanations
content related to historical events, especially concerning women's rights and social issues
New Auto-Interp
Negative Logits
Identyfik
-0.74
équip
-0.56
annonces
-0.52
-0.52
expéri
-0.50
makeConstraints
-0.49
testen
-0.49
matum
-0.49
Spoljašnje
-0.49
واعد
-0.49
POSITIVE LOGITS
historians
1.75
historical
1.64
historian
1.55
histor
1.49
Historical
1.46
historical
1.44
Historical
1.42
history
1.33
Histor
1.29
histories
1.28
Activations Density 0.538%