INDEX
Explanations
specific years and other numerical values related to events or timelines
New Auto-Interp
Negative Logits
ua
-0.16
agos
-0.15
bots
-0.15
ajo
-0.15
azzo
-0.14
Reeves
-0.14
agma
-0.14
ãĥ¼ãĥĢ
-0.13
ansen
-0.13
ese
-0.13
POSITIVE LOGITS
strup
0.19
ADER
0.17
intermediate
0.16
ahun
0.15
è¯ī
0.14
agens
0.14
ervo
0.14
stom
0.13
sv
0.13
TOT
0.13
Activations Density 0.009%