INDEX
Explanations
proper names, particularly the name "Rebecca 9"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
251
+0.11
0.4%
687
+0.10
0.3%
61
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1343
+0.11
0.04
1120
+0.10
0.04
690
+0.10
0.04
Negative Logits
<bos>
-0.79
-0.67
ByVersion
-0.63
<?
-0.61
SequentialGroup
-0.55
ⓧ
-0.55
qiang
-0.54
onSave
-0.53
обеди
-0.52
énégal
-0.52
POSITIVE LOGITS
Rebecca
1.09
véhic
1.01
Rebecca
1.00
kac
0.97
silikon
0.94
lele
0.92
jaya
0.91
affor
0.91
saba
0.91
aussitôt
0.91
Activations Density 0.284%