INDEX
Explanations
details related to runtime and page dimensions of documents
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.28
1.0%
1013
+0.15
0.6%
297
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
776
+0.28
0.07
297
+0.15
0.05
147
+0.12
0.04
Negative Logits
<bos>
-1.66
/**
-0.94
ⓧ
-0.82
-0.80
/*
-0.79
RemoveField
-0.75
="#"><
-0.65
HasIndex
-0.62
//
-0.61
AlterField
-0.60
POSITIVE LOGITS
sappi
1.03
😍😍
0.93
😭😭
0.91
maneu
0.89
Mentre
0.88
🥲
0.88
blackpink
0.88
🤣🤣
0.87
❤️❤️
0.86
Perci
0.86
Activations Density 0.301%