INDEX
Explanations
references to maritime or naval activities
New Auto-Interp
Negative Logits
Walking
-0.17
walk
-0.17
Walk
-0.16
migr
-0.16
amel
-0.16
ships
-0.16
Trucks
-0.16
ship
-0.15
Boat
-0.15
Drivers
-0.15
POSITIVE LOGITS
mo
0.35
anchor
0.33
anchored
0.32
anchors
0.31
anch
0.30
anchor
0.30
Anchor
0.28
.anchor
0.27
anchors
0.25
anch
0.25
Activations Density 0.076%