INDEX
Explanations
references to historical conflicts and events, particularly those related to wars and social issues
New Auto-Interp
Negative Logits
orge
-0.06
unsub
-0.06
TC
-0.05
Tribe
-0.05
imper
-0.05
COPYRIGHT
-0.05
Animalia
-0.05
q
-0.05
2
-0.05
zw
-0.05
POSITIVE LOGITS
-era
0.11
era
0.10
heritage
0.10
Legacy
0.09
legacy
0.09
Era
0.09
legacy
0.09
anniversary
0.09
era
0.09
history
0.09
Activations Density 0.054%