INDEX
Explanations
terms related to ownership and possession
New Auto-Interp
Negative Logits
otte
-0.18
ÏĢοÏį
-0.16
avia
-0.15
Vest
-0.15
-LAST
-0.15
iena
-0.15
iene
-0.14
atta
-0.14
Schwe
-0.14
deaux
-0.14
POSITIVE LOGITS
Weinstein
0.17
TITLE
0.15
Dos
0.14
ikan
0.14
-lfs
0.14
ikat
0.14
806
0.14
sing
0.14
zel
0.14
anus
0.14
Activations Density 0.001%