INDEX
Explanations
email signatures with professional contact information
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.10
0.4%
1387
+0.05
0.2%
1965
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1507
+0.10
0.04
631
+0.05
0.03
1301
+0.05
0.03
Negative Logits
<bos>
-1.29
<?
-1.08
ⓧ
-1.01
-1.01
<?
-0.90
enable
-0.80
engage
-0.79
public
-0.79
regulate
-0.79
expand
-0.78
POSITIVE LOGITS
Juf
2.32
accla
2.20
affor
2.18
increa
2.17
maneu
2.16
stockholm
2.13
ftu
2.13
fta
2.13
véhic
2.11
Intere
2.09
Activations Density 0.111%