INDEX
Explanations
references to legal or financial matters, such as bankruptcy and pension protection
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2034
+0.09
0.2%
1727
+0.08
0.2%
1445
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
310
+0.09
0.03
1445
+0.08
0.06
264
+0.08
0.02
Negative Logits
leonardo
-1.02
sergio
-1.01
gabri
-0.98
roberto
-0.97
jorge
-0.97
sandra
-0.96
lola
-0.95
claudia
-0.93
chery
-0.92
stefan
-0.92
POSITIVE LOGITS
ISupport
0.63
therefore
0.58
かわらず
0.53
shouldn
0.51
deserve
0.51
suddenly
0.51
therefore
0.50
Unfortunately
0.49
cannot
0.49
nên
0.49
Activations Density 0.424%