INDEX
Explanations
similarities and differences in genetic makeup
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
198
+0.10
0.3%
876
+0.10
0.3%
1220
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1220
+0.10
0.04
1287
+0.10
0.03
1816
+0.09
0.03
Negative Logits
€/
-0.67
€/
-0.66
torner
-0.66
notor
-0.62
€)
-0.62
textil
-0.60
€)
-0.59
parteci
-0.59
__":
-0.59
Historio
-0.59
POSITIVE LOGITS
Iden
1.02
identical
0.86
Similarity
0.81
identical
0.79
malheureux
0.73
wikihow
0.73
indistingu
0.72
travis
0.71
identically
0.71
similarity
0.71
Activations Density 0.471%