INDEX
Explanations
plural nouns, particularly those ending in 'er' or 'ers'
New Auto-Interp
Negative Logits
phere
-0.16
beck
-0.16
arro
-0.15
uir
-0.15
ajs
-0.15
ton
-0.14
.onView
-0.14
иной
-0.14
((-
-0.14
خت
-0.14
POSITIVE LOGITS
repid
0.17
iego
0.17
emiah
0.14
.dylib
0.14
owied
0.14
нед
0.14
emo
0.14
oulouse
0.14
etails
0.14
çŁ¥
0.13
Activations Density 0.101%