INDEX
Explanations
references to possession or control, particularly through the metaphor of "hands" and "eyes."
New Auto-Interp
Negative Logits
595
-0.07
olik
-0.07
767
-0.06
iali
-0.06
anan
-0.06
arak
-0.06
fried
-0.06
gist
-0.06
ya
-0.06
-sided
-0.06
POSITIVE LOGITS
Ã¥r
0.07
jmu
0.07
vala
0.07
ITH
0.07
addle
0.07
ulo
0.07
pÅĻip
0.07
моÑģ
0.06
ARSER
0.06
itzer
0.06
Activations Density 0.011%