INDEX
Explanations
phrases related to household cleaning products and reviews
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.18
1.0%
605
+0.04
0.2%
2019
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
395
+0.18
0.07
1602
+0.04
0.07
605
+0.04
0.04
Negative Logits
<bos>
-2.63
///**
-0.93
/**
-0.85
<tfoot>
-0.81
/*
-0.81
MarshalTo
-0.78
BUYER
-0.78
-0.78
<?
-0.77
/***
-0.75
POSITIVE LOGITS
maneu
2.30
affor
2.27
stockholm
2.13
accla
2.12
impra
2.07
increa
1.99
reluct
1.99
shenan
1.98
strick
1.96
lidl
1.95
Activations Density 1.221%