INDEX
Explanations
mentions of wheelchairs or objects related to mobility assistance
references to wheelchairs and related mobility devices
New Auto-Interp
Negative Logits
abund
-0.79
atio
-0.75
uality
-0.73
nces
-0.72
rued
-0.71
Kafka
-0.68
entially
-0.67
WARN
-0.67
Seym
-0.66
natureconservancy
-0.66
POSITIVE LOGITS
chair
1.07
chairs
0.93
wright
0.90
wheelchair
0.78
ffe
0.75
pod
0.75
fold
0.72
accessible
0.72
SPA
0.68
fitted
0.67
Activations Density 0.034%