INDEX
Explanations
texts discussing news, articles, and comments sections on various topics
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.21
0.7%
1150
+0.09
0.3%
1008
+0.07
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1685
+0.21
0.05
1973
+0.09
0.05
106
+0.07
0.05
Negative Logits
<bos>
-1.78
/***
-0.69
HasColumnType
-0.62
HasIndex
-0.61
onBind
-0.59
loài
-0.58
pudesse
-0.57
setViewName
-0.56
Vegeu
-0.56
Открыть
-0.56
POSITIVE LOGITS
maneu
1.64
affor
1.63
disagre
1.58
increa
1.52
impra
1.47
accla
1.46
withal
1.44
unspeak
1.42
bandung
1.40
jaya
1.38
Activations Density 0.282%