INDEX
Explanations
references to familial relationships and interactions
New Auto-Interp
Negative Logits
ober
-0.17
damer
-0.16
gradable
-0.15
BoxLayout
-0.15
ucer
-0.14
istrovstvÃŃ
-0.14
ortho
-0.14
SetName
-0.14
ASCADE
-0.14
recurs
-0.14
POSITIVE LOGITS
,
0.17
log
0.16
574
0.15
de
0.14
ipc
0.14
store
0.14
fist
0.14
genitals
0.14
ãģĺ
0.14
soft
0.14
Activations Density 0.089%