INDEX
Explanations
monetary transactions and economic relationships
New Auto-Interp
Negative Logits
geist
-0.17
thal
-0.16
akis
-0.16
ottom
-0.16
awi
-0.15
gne
-0.14
shm
-0.14
tep
-0.14
عر
-0.14
etting
-0.14
POSITIVE LOGITS
inet
0.14
keys
0.14
kako
0.14
ngang
0.13
frage
0.13
Monter
0.13
ÙħÙĤ
0.13
иÑĤов
0.13
kä
0.13
urf
0.13
Activations Density 0.219%