INDEX
Explanations
specific mentions of technology and international relations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1177
+0.14
0.4%
906
+0.11
0.3%
1741
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
790
+0.14
0.03
2002
+0.11
0.03
906
+0.10
0.00
Negative Logits
ecru
-1.11
hairc
-1.02
swarovski
-0.97
tupperware
-0.94
linden
-0.91
peppa
-0.91
bandeau
-0.84
riviera
-0.83
hoody
-0.82
tille
-0.81
POSITIVE LOGITS
<bos>
0.71
Ilustra
0.64
lenker
0.58
Autoritní
0.53
Gemeinsame
0.52
&___
0.51
Ekster
0.49
Literat
0.48
Inggris
0.48
UnusedPrivate
0.47
Activations Density 0.349%