INDEX
Explanations
phrases related to organization and event logistics
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
678
+0.12
0.3%
50
+0.09
0.3%
1553
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
678
+0.12
0.06
16
+0.09
0.07
919
+0.08
0.01
Negative Logits
OGND
-0.59
"..\..\..\
-0.58
illoma
-0.55
oprecip
-0.53
GeneratedCode
-0.51
WriteBarrier
-0.50
AssemblyTitle
-0.50
IsUnicode
-0.50
ImageBackground
-0.50
addContainerGap
-0.49
POSITIVE LOGITS
disagre
1.13
thut
1.09
intersper
1.04
hcm
1.02
shenan
1.00
Simult
0.99
territo
0.97
olx
0.97
strick
0.97
indestru
0.97
Activations Density 0.799%