INDEX
Explanations
references to substances that can have therapeutic effects on mental or emotional well-being
New Auto-Interp
Negative Logits
éĺħ读次æķ°
-0.25
ëį°ìĿ´íĬ¸
-0.21
and
-0.21
to
-0.21
in
-0.20
h
-0.20
out
-0.20
a
-0.19
ex
-0.19
all
-0.18
POSITIVE LOGITS
çłĶç©¶
0.23
åıijå±ķ
0.21
ç§ijåѦ
0.21
çłĶ
0.20
é¢ĨåŁŁ
0.20
æĬĢæľ¯
0.20
ä½ĵç³»
0.19
åĮ»åѦ
0.19
åѦ
0.19
éĿ©
0.19
Activations Density 0.006%