INDEX
Explanations
the term "rush" and its variations in different contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.18
1.0%
555
+0.15
0.9%
1272
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
555
+0.18
0.02
1272
+0.15
0.02
397
+0.13
0.02
Negative Logits
<bos>
-2.50
/***
-0.77
glEnd
-0.70
},{
-0.69
alignSelf
-0.67
marginHorizontal
-0.67
SourceChecksum
-0.66
VIAF
-0.65
module
-0.65
|}
-0.64
POSITIVE LOGITS
affor
1.46
scrat
1.37
unden
1.35
increa
1.33
strick
1.33
swarovski
1.32
jurassic
1.31
casio
1.31
unce
1.30
madonna
1.29
Activations Density 0.056%