INDEX
Explanations
terms related to death and mourning
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.17
0.7%
1407
+0.12
0.5%
596
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
596
+0.17
0.02
498
+0.12
0.02
1013
+0.12
0.03
Negative Logits
<bos>
-2.12
<?
-0.75
-0.66
Lịch
-0.64
Nội
-0.64
/*!
-0.63
impuls
-0.63
ⓧ
-0.62
Исто
-0.62
HasColumnType
-0.61
POSITIVE LOGITS
maneu
1.73
impra
1.51
?...
1.47
emphat
1.47
increa
1.45
:'(
1.43
Juf
1.42
strick
1.41
reluct
1.39
affor
1.37
Activations Density 0.098%