INDEX
Explanations
references to nautical terms and maritime events
New Auto-Interp
Negative Logits
Sailor
-0.15
Aviation
-0.15
Truck
-0.15
lut
-0.15
CHA
-0.15
exe
-0.15
ash
-0.15
ropp
-0.15
Entr
-0.14
exe
-0.14
POSITIVE LOGITS
battles
0.29
vessel
0.27
vessels
0.26
scho
0.26
Battles
0.26
merchant
0.24
vess
0.24
liner
0.23
clip
0.22
ÑĤепло
0.22
Activations Density 0.130%