INDEX
Explanations
phrases related to the duration or continuity of actions or events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.19
0.8%
405
+0.13
0.5%
577
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
404
+0.19
0.03
1661
+0.13
0.03
405
+0.12
0.03
Negative Logits
<bos>
-2.28
/***
-0.97
-0.89
ⓧ
-0.82
<?
-0.76
deinit
-0.73
/*!
-0.71
///**
-0.70
#
-0.64
ReactDOM
-0.63
POSITIVE LOGITS
wien
0.94
drey
0.91
bloss
0.87
yong
0.85
sii
0.84
lele
0.82
maneu
0.81
ohr
0.79
bandung
0.79
kef
0.78
Activations Density 0.163%