INDEX
Explanations
words related to warfare and combat
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
517
+0.15
0.8%
50
+0.14
0.8%
406
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
406
+0.15
0.03
517
+0.14
0.03
1520
+0.14
0.02
Negative Logits
<bos>
-2.63
="#"
-0.71
lateinit
-0.71
ൊ
-0.69
initComponents
-0.69
://
-0.67
</
-0.67
ClientSize
-0.66
addComponent
-0.66
></
-0.65
POSITIVE LOGITS
swarovski
2.11
eiffel
2.08
milano
2.04
napoli
2.02
increa
1.99
affor
1.96
peppa
1.95
maneu
1.94
emphat
1.94
verona
1.92
Activations Density 0.064%