INDEX
Explanations
text related to legislation, regulations, and practices concerning discrimination based on disability
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.16
0.9%
1328
+0.11
0.6%
479
+0.10
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
258
+0.16
0.02
1077
+0.11
0.02
1553
+0.10
0.02
Negative Logits
<bos>
-2.96
ⓧ
-0.89
/**
-0.82
-0.72
/***
-0.68
rungsseite
-0.63
///**
-0.62
/*!
-0.61
<?
-0.60
//---
-0.60
POSITIVE LOGITS
Karang
1.30
Minang
1.29
saar
1.28
jaya
1.26
dises
1.23
bandung
1.22
jawa
1.18
maksi
1.17
Disability
1.17
alha
1.16
Activations Density 0.090%