INDEX
Explanations
phrases related to branches, railways, and infrastructure
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.14
0.8%
1407
+0.12
0.7%
1331
+0.09
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1026
+0.14
0.02
1331
+0.12
0.01
239
+0.09
0.02
Negative Logits
<bos>
-3.09
ⓧ
-0.73
public
-0.69
//---
-0.68
терак
-0.64
<?
-0.64
create
-0.62
Identyfik
-0.61
oredCriteria
-0.61
pub
-0.60
POSITIVE LOGITS
ftu
1.45
stockholm
1.41
thut
1.39
vns
1.36
fta
1.36
milf
1.35
ftre
1.35
disagre
1.35
reft
1.31
unwarran
1.31
Activations Density 0.062%