INDEX
Explanations
photographs
references to photographs
New Auto-Interp
Negative Logits
steen
-0.74
woods
-0.73
onge
-0.68
inence
-0.67
road
-0.67
sei
-0.64
ricular
-0.62
lling
-0.62
govern
-0.62
ught
-0.62
POSITIVE LOGITS
ographs
1.08
photographs
1.03
photographed
1.03
Photograph
1.00
photos
0.99
photograph
0.96
Phot
0.96
Phot
0.94
photographers
0.93
Photographer
0.93
Activations Density 0.021%