INDEX
Explanations
references to detailed reports and discussions in a formal context
New Auto-Interp
Negative Logits
ipple
-0.16
beeld
-0.15
elter
-0.15
mens
-0.14
azo
-0.14
fk
-0.14
aleza
-0.14
NF
-0.14
ailable
-0.14
-none
-0.13
POSITIVE LOGITS
estre
0.15
agram
0.14
untu
0.14
uben
0.14
ednou
0.14
isoft
0.14
olu
0.14
present
0.14
eye
0.13
ucher
0.13
Activations Density 0.012%