INDEX
Explanations
the name "Kyle" in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1964
+0.18
0.8%
31
+0.18
0.8%
1325
+0.17
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
981
+0.18
0.05
395
+0.18
0.04
1177
+0.17
0.02
Negative Logits
unspeak
-0.62
shenan
-0.60
darted
-0.59
Driscoll
-0.58
disreg
-0.58
Shaffer
-0.56
Trotter
-0.56
roused
-0.55
impelled
-0.55
Felton
-0.55
POSITIVE LOGITS
Kyle
1.19
Kyle
1.16
kyle
0.90
kram
0.80
Võ
0.74
franz
0.74
rege
0.73
elek
0.71
kosme
0.70
lemp
0.70
Activations Density 0.271%