INDEX
Explanations
words related to flight or flying
references to flying or aerial activities
New Auto-Interp
Negative Logits
Cumber
-0.85
uary
-0.79
contraction
-0.75
Wem
-0.71
essee
-0.67
aido
-0.67
ricting
-0.65
_>
-0.65
ipation
-0.65
urion
-0.64
POSITIVE LOGITS
wheel
0.99
plane
0.98
whe
0.92
planes
0.90
weight
0.85
walk
0.84
cat
0.83
hawk
0.82
leaf
0.81
past
0.81
Activations Density 0.041%