INDEX
Explanations
mentions of the name "Matt."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
156
+0.18
1.0%
369
+0.17
1.0%
376
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
289
+0.18
0.02
177
+0.17
0.02
385
+0.14
0.02
Negative Logits
ı
-2.69
¿½
-2.47
ĥ½
-2.38
§
-2.36
İ
-2.35
ĵ
-2.31
¿
-2.31
¼
-2.31
Ļª
-2.30
®
-2.30
POSITIVE LOGITS
opan
1.90
film
1.78
iej
1.68
icillin
1.68
uet
1.68
park
1.67
ie
1.59
films
1.59
ieux
1.57
uelle
1.55
Activations Density 0.024%