INDEX
Explanations
the word "like" used in various contexts
New Auto-Interp
Negative Logits
Æ¡
-0.16
нÑĥÑĤÑĮÑģÑı
-0.16
elay
-0.16
æ¿
-0.15
Baker
-0.15
vais
-0.15
æľĿ
-0.15
enses
-0.15
ooky
-0.14
ساÙħ
-0.14
POSITIVE LOGITS
ction
0.15
if
0.15
post
0.15
ame
0.15
Lear
0.14
unga
0.14
post
0.14
ANJI
0.14
age
0.14
image
0.13
Activations Density 0.029%