INDEX
Explanations
numerical data and figures
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1343
+0.16
0.5%
137
+0.14
0.5%
227
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1343
+0.16
0.09
1009
+0.14
0.04
184
+0.12
0.02
Negative Logits
StoreMessageInfo
-0.81
gynhyrchwyd
-0.79
Administrativna
-0.74
<bos>
-0.73
հղումներ
-0.72
SourceChecksum
-0.71
otomatig
-0.69
AssemblyCulture
-0.68
Italijani
-0.67
richTextPanel
-0.65
POSITIVE LOGITS
vns
1.36
fta
1.34
»>
1.33
ftu
1.32
fign
1.32
fep
1.32
squa
1.29
fath
1.29
fuf
1.28
increa
1.28
Activations Density 0.666%