INDEX
Explanations
terms related to military and combat scenarios
New Auto-Interp
Negative Logits
zcze
-0.18
alem
-0.15
errick
-0.14
-controller
-0.14
emode
-0.14
cott
-0.14
phies
-0.14
PoÄįet
-0.13
akhir
-0.13
acer
-0.13
POSITIVE LOGITS
cav
0.29
cavity
0.29
Foot
0.26
Huss
0.24
Horse
0.24
cu
0.23
foot
0.23
horse
0.23
Fus
0.23
fus
0.23
Activations Density 0.030%