INDEX
Explanations
infinitive verbs expressing intentions or actions
New Auto-Interp
Negative Logits
Goldberg
-0.14
addon
-0.14
iddi
-0.14
ÙĪÛĮØ´
-0.14
Millenn
-0.13
аÑĤов
-0.13
rah
-0.13
icher
-0.13
zin
-0.13
ãĥ¼ãĤ¹
-0.13
POSITIVE LOGITS
ICA
0.15
eel
0.15
andel
0.14
cine
0.14
اÙĨت
0.14
ÑīеннÑı
0.13
اÛĮÙĨÚ©Ùĩ
0.13
thôi
0.13
UTE
0.13
gnu
0.13
Activations Density 0.086%