INDEX
Explanations
terms related to government surveillance and privacy issues
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.26
1.0%
1842
+0.13
0.5%
198
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
946
+0.26
0.04
1842
+0.13
0.02
198
+0.12
0.04
Negative Logits
<bos>
-3.17
ⓧ
-0.89
/*!
-0.65
/***
-0.61
lateinit
-0.58
/**
-0.57
finish
-0.56
-0.55
fflush
-0.53
#![
-0.52
POSITIVE LOGITS
bandung
1.36
lele
1.24
Palembang
1.19
jaya
1.18
Pekan
1.18
surabaya
1.17
milano
1.16
santiago
1.15
bayern
1.15
Jambi
1.14
Activations Density 0.365%