INDEX
Explanations
references to specific years
New Auto-Interp
Negative Logits
today
-0.27
aujourd
-0.24
heute
-0.23
nowadays
-0.21
oggi
-0.20
ÑģегоднÑı
-0.20
today
-0.19
hoje
-0.19
ÑģейÑĩаÑģ
-0.19
tonight
-0.19
POSITIVE LOGITS
alone
0.17
alone
0.16
(Expected
0.16
inery
0.15
insky
0.15
ÙħÛĮÙĦادÛĮ
0.15
lify
0.14
lerde
0.14
ino
0.14
marks
0.14
Activations Density 0.059%