INDEX
Explanations
mentions of significant historical figures and their achievements
New Auto-Interp
Negative Logits
lds
-0.16
(æ°´
-0.15
okable
-0.14
713
-0.14
.DOM
-0.14
ì°¨
-0.13
nds
-0.13
_since
-0.13
nee
-0.13
orama
-0.13
POSITIVE LOGITS
legend
0.20
ovu
0.16
wrote
0.15
recorded
0.15
died
0.15
Ingram
0.14
himself
0.14
bi
0.14
later
0.14
proto
0.14
Activations Density 0.391%