INDEX
Explanations
web links related to informative articles or resources
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1343
+0.20
0.6%
1403
+0.12
0.3%
2019
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
382
+0.20
0.03
1840
+0.12
0.01
562
+0.11
0.02
Negative Logits
unspeak
-1.45
indestru
-1.33
horrend
-1.26
hairc
-1.26
intersper
-1.26
impra
-1.26
shenan
-1.24
indescri
-1.24
beaute
-1.23
apprehen
-1.18
POSITIVE LOGITS
html
0.99
htm
0.80
php
0.77
xml
0.72
jpg
0.69
0.68
aspx
0.65
=".
0.65
PicClick
0.64
txt
0.64
Activations Density 0.096%