INDEX
Explanations
words related to possessions and ownership
New Auto-Interp
Negative Logits
idable
-0.15
040
-0.15
kop
-0.14
hare
-0.14
_TEMP
-0.14
и
-0.13
ously
-0.13
лож
-0.13
Chamber
-0.12
Page
-0.12
POSITIVE LOGITS
/goto
0.17
abei
0.16
enet
0.15
MQ
0.15
alendar
0.14
(es
0.14
alach
0.14
ëĦ·
0.14
esson
0.14
ruk
0.14
Activations Density 0.017%