INDEX
Explanations
phrases related to statements or reports
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1150
+0.14
0.5%
1133
+0.13
0.5%
1296
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
899
+0.14
0.04
1296
+0.13
0.04
1133
+0.13
0.03
Negative Logits
gabri
-1.07
affez
-0.99
javier
-0.99
batte
-0.98
roberto
-0.97
felipe
-0.96
alberto
-0.96
nicolas
-0.95
casio
-0.95
sappi
-0.95
POSITIVE LOGITS
statement
1.50
statements
1.36
statement
1.34
Statement
1.28
Statement
1.24
statements
1.19
Statements
1.16
STATEMENT
1.13
STATEMENT
1.10
Statements
1.03
Activations Density 0.064%