INDEX
Explanations
years and locations mentioned in a professional context
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.11
0.5%
938
+0.11
0.5%
1677
+0.11
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
227
+0.11
0.07
143
+0.11
0.06
1677
+0.11
0.04
Negative Logits
<bos>
-2.36
<?
-0.81
ByVersion
-0.80
&___
-0.74
Configurer
-0.70
RuleContext
-0.69
AddWithValue
-0.69
endregion
-0.68
汉
-0.68
/**
-0.68
POSITIVE LOGITS
madonna
1.94
affor
1.78
snoopy
1.73
Abbé
1.73
reluct
1.73
shenan
1.69
milf
1.68
stockholm
1.68
accla
1.67
perfet
1.66
Activations Density 0.580%