INDEX
Explanations
information related to the effects of lead exposure on health
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
876
+0.10
0.3%
617
+0.09
0.3%
964
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
41
+0.10
0.06
1380
+0.09
0.01
2002
+0.09
0.03
Negative Logits
***!
-0.64
GOTREF
-0.62
Välislingid
-0.61
__':
-0.59
<>());
-0.59
]")]
-0.58
<>",
-0.58
للاسماء
-0.57
Хьажоргаш
-0.56
Personensuche
-0.56
POSITIVE LOGITS
ftu
1.41
fta
1.36
fuf
1.33
ftre
1.31
thut
1.31
waer
1.30
poff
1.30
disagre
1.27
fto
1.26
fte
1.25
Activations Density 0.442%