INDEX
Explanations
discussions or descriptions focusing on viewpoints or attitudes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
528
+0.14
0.5%
1677
+0.11
0.4%
1233
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
528
+0.14
0.02
121
+0.11
0.02
240
+0.10
0.02
Negative Logits
proprement
-0.64
Winf
-0.61
enrique
-0.60
Oester
-0.60
Uli
-0.59
idéia
-0.58
scatt
-0.58
brilla
-0.57
reiv
-0.57
Mier
-0.56
POSITIVE LOGITS
perspective
1.46
perspectives
1.33
Perspective
1.33
perspective
1.23
Perspective
1.19
Perspectives
1.04
pectives
1.01
PERSPECT
1.01
viewpoint
0.96
perspectiva
0.94
Activations Density 0.087%