INDEX
Explanations
mentions of firearms and related terms
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
478
+0.21
0.8%
1870
+0.17
0.7%
406
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1870
+0.21
0.04
1438
+0.17
0.04
227
+0.12
0.05
Negative Logits
confé
-0.61
kompati
-0.57
Konkur
-0.57
fédé
-0.57
dão
-0.55
Pautan
-0.54
prévue
-0.53
恣
-0.53
djang
-0.53
strona
-0.52
POSITIVE LOGITS
minValue
0.60
cavalli
0.58
vapore
0.56
firearms
0.54
sement
0.53
signora
0.52
fratelli
0.51
workforce
0.50
lefs
0.50
pæ
0.49
Activations Density 0.334%