INDEX
Explanations
phrases that express abundance or quantity
New Auto-Interp
Negative Logits
ones
-0.15
988
-0.15
389
-0.15
ubby
-0.15
jedn
-0.14
crowds
-0.14
-addon
-0.14
анÑģи
-0.14
etto
-0.13
perch
-0.13
POSITIVE LOGITS
nul
0.15
ë°±
0.14
uns
0.14
ìĺ
0.14
heritance
0.14
ationale
0.14
ãĥ¼ãĥį
0.14
prost
0.14
izzo
0.14
rightness
0.14
Activations Density 0.054%