INDEX
Explanations
the letter 'h' in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.21
1.3%
950
+0.14
0.9%
397
+0.13
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1343
+0.21
0.02
950
+0.14
0.02
397
+0.13
0.02
Negative Logits
<bos>
-2.53
لينكات
-0.63
Kontrola
-0.60
Nå
-0.60
"..\..\..\
-0.60
GEBURTSDATUM
-0.59
Economía
-0.58
MockBean
-0.58
ⓧ
-0.57
Xuất
-0.57
POSITIVE LOGITS
h
1.18
bourgeo
1.07
h
1.06
Hano
1.06
quoique
1.04
fath
1.03
maroc
1.02
Bén
0.99
afric
0.96
parch
0.95
Activations Density 0.031%