INDEX
Explanations
references to World War I and related historical documents
New Auto-Interp
Negative Logits
SizeMode
-0.16
avig
-0.15
WithPath
-0.14
-NLS
-0.14
Ñĸж
-0.14
_backup
-0.13
gravity
-0.13
-liter
-0.13
/problems
-0.13
chner
-0.13
POSITIVE LOGITS
Hist
0.18
Military
0.15
hist
0.15
mater
0.15
historians
0.15
historian
0.15
isseur
0.15
ctrine
0.15
Hist
0.15
Regular
0.14
Activations Density 0.018%