INDEX
Explanations
phrases related to technical or legal concepts and discussions
New Auto-Interp
Negative Logits
ceb
-0.17
.people
-0.16
ici
-0.15
somebody
-0.15
someone
-0.15
avo
-0.15
oneself
-0.15
ilton
-0.15
па
-0.15
ака
-0.15
POSITIVE LOGITS
/us
0.18
nger
0.17
Pic
0.15
dz
0.15
Giov
0.15
à¹ĥà¸Ļà¸ģาร
0.14
á»ī
0.14
opis
0.14
ETS
0.14
ë§Ŀ
0.14
Activations Density 0.647%