INDEX
Explanations
affiliations with academic research or projects, particularly in the digital humanities
New Auto-Interp
Negative Logits
arella
-0.19
egend
-0.15
باش
-0.15
usercontent
-0.15
gren
-0.14
enÃŃ
-0.14
vál
-0.14
Cases
-0.14
á»ĭ
-0.14
æŃ¡
-0.14
POSITIVE LOGITS
Exped
0.16
_HOT
0.15
Smithsonian
0.15
libr
0.15
\Lib
0.14
/Library
0.14
vertise
0.14
Fur
0.14
Liberty
0.14
lib
0.14
Activations Density 0.010%