INDEX
Explanations
information related to local politics and events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
382
+0.31
1.6%
50
+0.25
1.3%
2034
+0.23
1.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
382
+0.31
0.24
2034
+0.25
0.20
1535
+0.23
0.10
Negative Logits
<bos>
-3.54
ⓧ
-1.27
<?
-0.96
/**
-0.95
///**
-0.94
-0.91
defaultstate
-0.90
AssemblyCompany
-0.87
الحره
-0.85
springfox
-0.85
POSITIVE LOGITS
maneu
1.40
shenan
1.35
accla
1.32
resear
1.20
philanth
1.19
unspeak
1.18
reluct
1.17
volunte
1.15
disreg
1.15
fortn
1.15
Activations Density 1.215%