INDEX
Explanations
biographical details about actors and actresses
New Auto-Interp
Negative Logits
dyn
-0.15
ÑĤов
-0.15
Ø
-0.14
munition
-0.14
ông
-0.14
iom
-0.14
latin
-0.14
ãĤ¹ãĤ¿ãĥ¼
-0.14
ág
-0.13
Ø·Ùĩ
-0.13
POSITIVE LOGITS
екаÑĢ
0.18
ÑıÑĩ
0.15
rus
0.14
eldon
0.14
UCT
0.14
Weber
0.14
lip
0.14
ارب
0.14
تÙĦ
0.14
ãģ¤ãģ¶
0.14
Activations Density 0.145%