INDEX
Explanations
articles and determiners in a text
New Auto-Interp
Negative Logits
ÏĥÏĦή
-0.15
odial
-0.15
ï¼»
-0.15
_party
-0.14
eus
-0.14
ombo
-0.14
taxis
-0.14
bÃŃr
-0.14
Franti
-0.14
заб
-0.14
POSITIVE LOGITS
iaz
0.17
490
0.16
295
0.15
125
0.15
195
0.15
294
0.14
aster
0.14
-INF
0.14
401
0.14
111
0.14
Activations Density 0.016%