INDEX
Explanations
references to wars and battles throughout history
New Auto-Interp
Negative Logits
jeme
-0.15
otherwise
-0.15
util
-0.15
pedia
-0.15
str
-0.15
gia
-0.14
tink
-0.14
regor
-0.14
roke
-0.14
sever
-0.14
POSITIVE LOGITS
ienes
0.16
ybrid
0.16
planes
0.15
ORB
0.15
_$_
0.15
OffsetTable
0.15
esel
0.14
ToProps
0.14
unday
0.14
PEAR
0.14
Activations Density 0.050%