INDEX
Explanations
references to digital humanities and interdisciplinary research
New Auto-Interp
Negative Logits
jal
-0.15
sea
-0.15
_Tis
-0.14
erox
-0.14
bjerg
-0.14
sal
-0.14
ç½²
-0.13
hu
-0.13
bur
-0.13
_inches
-0.13
POSITIVE LOGITS
bare
0.19
ivar
0.18
nun
0.17
itag
0.17
technology
0.15
ë§ŀ
0.14
tring
0.14
å®Ļ
0.14
edm
0.14
ens
0.14
Activations Density 0.028%