INDEX
Explanations
start of sentences or clauses
New Auto-Interp
Negative Logits
*
-1.01
grandchildren
-0.96
Externí
-0.96
>
-0.96
Kaieteur
-0.95
centers
-0.93
enero
-0.91
It
-0.91
ingeki
-0.91
(«
-0.90
POSITIVE LOGITS
这句话
1.64
then
1.45
that
1.26
followed
1.22
this
1.09
thats
1.06
replied
1.05
этого
1.02
THAT
0.95
gemeint
0.94
Activations Density 0.071%