INDEX
Explanations
phrases related to political activities and events
New Auto-Interp
Negative Logits
ismet
-0.16
Islam
-0.16
Islam
-0.16
Mohammed
-0.15
bang
-0.15
India
-0.15
Mosque
-0.14
Apple
-0.14
Calvin
-0.14
Vive
-0.14
POSITIVE LOGITS
awy
0.19
alat
0.16
nech
0.16
eless
0.16
ilerden
0.15
etÃŃ
0.15
_elt
0.15
olars
0.15
772
0.15
Fay
0.15
Activations Density 0.258%