INDEX
Explanations
references to historical changes in locations and names within a contemporary context
New Auto-Interp
Negative Logits
vara
-0.17
originally
-0.16
abi
-0.16
SSERT
-0.15
sil
-0.14
cion
-0.14
ç£
-0.14
Wolff
-0.14
oose
-0.14
ibox
-0.13
POSITIVE LOGITS
oday
0.18
today
0.18
aujourd
0.17
today
0.17
moderne
0.16
ä»Ĭ天
0.16
enler
0.15
indow
0.15
oggi
0.15
heute
0.14
Activations Density 0.037%