INDEX
Explanations
references to garages
occurrences of the word "garage."
New Auto-Interp
Negative Logits
lihood
-0.94
vironment
-0.92
uality
-0.85
ciating
-0.84
emic
-0.78
Archdemon
-0.78
ebus
-0.76
inel
-0.75
Marketable
-0.75
tics
-0.74
POSITIVE LOGITS
garage
1.14
door
0.86
door
0.85
Garage
0.82
doors
0.81
chair
0.78
attic
0.77
stairs
0.75
dealership
0.74
Door
0.72
Activations Density 0.011%