INDEX
Explanations
instances of years mentioned in the text
New Auto-Interp
Negative Logits
aul
-0.15
lan
-0.15
surrounding
-0.15
ildo
-0.14
ba
-0.14
action
-0.14
Gang
-0.14
athing
-0.14
weather
-0.14
(
-0.14
POSITIVE LOGITS
kaar
0.16
avou
0.15
æ¸IJ
0.15
aire
0.14
essen
0.14
ÑĤÑĢон
0.14
isman
0.14
âb
0.14
éĬ·
0.14
_pemb
0.14
Activations Density 0.026%