INDEX
Explanations
verbs related to action and participation
New Auto-Interp
Negative Logits
Nej
-0.13
ransition
-0.12
reffen
-0.12
ogany
-0.12
yaptıģı
-0.12
Narrated
-0.12
Thrown
-0.12
EGIN
-0.12
ÑĢаÐ
-0.12
çĦ¶
-0.12
POSITIVE LOGITS
your
0.50
Your
0.47
Yourself
0.47
yourself
0.45
Your
0.38
yourselves
0.37
Them
0.37
able
0.36
me
0.35
ing
0.34
Activations Density 0.570%