INDEX
Explanations
written information or text related to various documents or publications
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1150
+0.13
0.4%
1385
+0.13
0.4%
490
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
490
+0.13
0.03
678
+0.13
0.05
71
+0.10
0.03
Negative Logits
hairc
-0.89
swarovski
-0.83
Shakspeare
-0.76
cushi
-0.75
snapback
-0.74
Membre
-0.74
»>
-0.73
murano
-0.72
matel
-0.71
tupperware
-0.71
POSITIVE LOGITS
printed
0.71
paper
0.64
printing
0.64
printed
0.58
booklet
0.55
Printed
0.54
0.54
printer
0.54
printers
0.51
sheets
0.51
Activations Density 0.707%