INDEX
Explanations
information related to serial killers and their behavior patterns
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2034
+0.25
0.8%
1699
+0.19
0.6%
382
+0.17
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
382
+0.25
0.09
195
+0.19
0.06
1896
+0.17
0.04
Negative Logits
ujedno
-0.92
Mejía
-0.89
Lmfao
-0.83
unwarran
-0.83
zbęd
-0.81
Marín
-0.79
mondeo
-0.79
azule
-0.78
churrasco
-0.78
viciss
-0.78
POSITIVE LOGITS
↵↵
0.74
<bos>
0.72
↵
0.68
uxe
0.63
↵↵↵
0.63
}.
0.62
.
0.58
</tr>
0.58
Wirkungen
0.58
;.
0.56
Activations Density 0.381%