INDEX
Explanations
references to people and entities in a relational context
New Auto-Interp
Negative Logits
enso
-0.15
672
-0.14
cks
-0.14
овани
-0.14
978
-0.14
969
-0.13
238
-0.13
ikh
-0.13
اذ
-0.13
Sür
-0.13
POSITIVE LOGITS
ARRANT
0.19
skyt
0.17
ãĤ¿ãĥ³
0.15
lemen
0.14
ุà¹ī
0.14
swick
0.14
SGlobal
0.14
rog
0.14
DTD
0.14
ÎķÎ¥
0.14
Activations Density 0.776%