INDEX
Explanations
phrases related to political campaigns and elections
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1253
+0.15
0.4%
964
+0.10
0.3%
344
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
416
+0.15
0.05
81
+0.10
0.03
647
+0.09
0.03
Negative Logits
rospy
-0.58
dziewczyn
-0.52
Customizable
-0.52
Washable
-0.50
Organisms
-0.49
noexcept
-0.49
<bos>
-0.48
shutil
-0.48
worin
-0.47
vielmehr
-0.47
POSITIVE LOGITS
uhr
0.63
Senat
0.61
Nguy
0.58
ucha
0.57
bayern
0.56
lccn
0.56
Dosen
0.56
Demokrat
0.55
sena
0.55
pse
0.55
Activations Density 0.417%