INDEX
Explanations
photography-related words and concepts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
789
+0.15
0.6%
1325
+0.12
0.4%
1872
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1018
+0.15
0.03
789
+0.12
0.03
1872
+0.12
0.02
Negative Logits
Iné
-0.71
calciatore
-0.60
télévis
-0.60
geslacht
-0.60
DockStyle
-0.58
Hentet
-0.58
Pozri
-0.57
Externé
-0.56
Gouver
-0.55
Asien
-0.55
POSITIVE LOGITS
photograph
1.09
photography
1.08
photographs
1.04
Photography
1.00
photographer
0.98
photographing
0.98
photographers
0.97
photographed
0.96
Photograph
0.92
Photographs
0.92
Activations Density 0.057%