INDEX
Explanations
the names and dates related to specific events, locations, and individuals
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
227
+0.15
0.4%
2034
+0.12
0.4%
1150
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
981
+0.15
0.08
227
+0.12
0.08
1483
+0.11
0.05
Negative Logits
Outros
-0.77
">...
-0.76
viciss
-0.74
">/
-0.72
Divulgação
-0.71
pamph
-0.68
Qualquer
-0.68
Dijo
-0.68
hdas
-0.68
occupe
-0.67
POSITIVE LOGITS
.
0.70
,
0.68
;
0.66
)
0.60
:
0.53
-,
0.52
),
0.49
,'
0.48
asas
0.48
',
0.48
Activations Density 0.425%