INDEX
Explanations
mentions of specific years or dates
New Auto-Interp
Negative Logits
751
-0.17
395
-0.16
786
-0.16
596
-0.16
683
-0.15
iani
-0.15
iel
-0.15
riba
-0.15
antium
-0.15
788
-0.15
POSITIVE LOGITS
804
0.17
507
0.17
103
0.16
301
0.16
409
0.16
608
0.16
912
0.15
assel
0.15
602
0.15
402
0.15
Activations Density 0.190%