INDEX
Explanations
mentions of safety gear, specifically helmets, and activities or contexts where helmets are needed
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1065
+0.11
0.3%
795
+0.08
0.3%
241
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1065
+0.11
0.02
690
+0.08
0.03
1385
+0.07
0.02
Negative Logits
<bos>
-1.11
WriteLiteral
-0.60
ⓧ
-0.58
<?
-0.56
JspWriter
-0.55
/**
-0.55
mustered
-0.54
ConstraintMaker
-0.53
contentLoaded
-0.53
onView
-0.52
POSITIVE LOGITS
helmet
2.69
helmets
2.55
Helmet
2.40
helmet
2.19
Helmet
2.15
casque
1.35
Hel
1.14
headset
1.12
casco
1.08
Headset
1.02
Activations Density 0.161%