INDEX
Explanations
references to military ships and their specifications
New Auto-Interp
Negative Logits
ç»ĩ
-0.16
ooth
-0.14
ä¸Ŀ
-0.14
ç·ł
-0.14
DOT
-0.14
669
-0.13
inel
-0.13
Rag
-0.13
598
-0.13
ØŃر
-0.13
POSITIVE LOGITS
aft
0.37
forward
0.33
fwd
0.32
stern
0.30
bow
0.30
fore
0.29
decks
0.29
Forward
0.28
deck
0.28
aba
0.28
Activations Density 0.031%