INDEX
Explanations
names of people and related titles in the context of film
New Auto-Interp
Negative Logits
acre
-0.15
ÑĦекÑĤив
-0.15
NU
-0.14
Official
-0.14
engin
-0.14
ownt
-0.14
oud
-0.14
upro
-0.14
elin
-0.13
Tran
-0.13
POSITIVE LOGITS
Barrier
0.16
ols
0.15
Lux
0.14
cad
0.14
ynos
0.14
293
0.13
295
0.13
ogonal
0.13
OLS
0.13
olson
0.13
Activations Density 0.074%