INDEX
Explanations
references to films and their elements related to war and conflict
New Auto-Interp
Negative Logits
ÑģÑĩеÑĤ
-0.16
inea
-0.15
fiat
-0.15
cak
-0.15
ỳ
-0.15
oftware
-0.14
ÑģÑĩ
-0.14
ilan
-0.14
oft
-0.14
ips
-0.14
POSITIVE LOGITS
ycz
0.16
idian
0.16
ánt
0.14
uido
0.14
Vol
0.14
887
0.14
Pow
0.14
837
0.13
Lav
0.13
oner
0.13
Activations Density 0.052%