INDEX
Explanations
the preposition "across" followed by a location or direction
the word "across."
New Auto-Interp
Negative Logits
nery
-0.83
spot
-0.65
etic
-0.65
zel
-0.64
FORE
-0.63
nas
-0.62
Lauder
-0.62
Parents
-0.60
ns
-0.59
Carr
-0.57
POSITIVE LOGITS
roads
1.00
atform
0.88
rooft
0.88
arrow
0.80
side
0.74
lines
0.74
urst
0.73
cutting
0.72
atcher
0.72
arm
0.71
Activations Density 0.027%