INDEX
Explanations
list items, places of worship, institutions
New Auto-Interp
Negative Logits
(
0.64
↵
0.54
arello
0.50
caveat
0.49
(“
0.48
تباينه
0.48
cryptic
0.47
tempered
0.46
šao
0.45
↵↵
0.45
POSITIVE LOGITS
अस्पतालों
0.61
t
0.58
prisons
0.57
synagogues
0.56
Hospitals
0.55
edificios
0.55
hospitals
0.55
를
0.54
Surgeons
0.54
to
0.53
Activations Density 0.476%