INDEX
Explanations
references to evidence and events related to specific populations and controversies
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.19
0.7%
1870
+0.12
0.4%
581
+0.08
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1870
+0.19
0.04
424
+0.12
0.03
1474
+0.08
0.04
Negative Logits
<bos>
-2.59
ⓧ
-0.76
esternos
-0.65
///**
-0.65
endwhile
-0.63
/***
-0.63
springfox
-0.62
Vegeu
-0.61
&___
-0.60
//}
-0.58
POSITIVE LOGITS
stockholm
1.08
Minang
1.07
Jambi
1.05
quran
1.02
Juf
1.02
Bekasi
1.02
leonardo
1.01
aen
0.99
Palembang
0.98
hcm
0.98
Activations Density 0.803%