INDEX
Explanations
names or references to specific individuals
New Auto-Interp
Negative Logits
ichel
-0.19
g
-0.17
.vertx
-0.15
stamp
-0.15
Sil
-0.15
\Abstract
-0.15
G
-0.14
Bram
-0.14
Rock
-0.14
neh
-0.14
POSITIVE LOGITS
ney
0.23
AGO
0.21
akov
0.20
NEY
0.20
ابÛĮ
0.19
neys
0.18
akis
0.18
rey
0.17
aco
0.17
.sw
0.16
Activations Density 0.036%