INDEX
Explanations
proper nouns related to a person named Kim
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1392
+0.15
0.9%
313
+0.14
0.8%
920
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1392
+0.15
0.03
1097
+0.14
0.03
920
+0.14
0.03
Negative Logits
<bos>
-1.53
ⓧ
-0.85
/**
-0.79
-0.78
<?
-0.74
/*
-0.68
yarnpkg
-0.64
#
-0.59
unsplash
-0.57
appuntamento
-0.57
POSITIVE LOGITS
Kim
1.63
Kim
1.60
KIM
1.48
kim
1.33
KIM
1.28
kim
1.12
Kimberley
0.99
Kimball
0.93
Kimberly
0.84
Kimberly
0.82
Activations Density 0.284%