INDEX
Explanations
phrases related to legal investigations and bureaucratic processes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1741
+0.15
0.5%
1967
+0.13
0.4%
674
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1187
+0.15
0.03
492
+0.13
0.04
1763
+0.11
0.03
Negative Logits
smtplib
-0.75
PLWABN
-0.70
pymysql
-0.70
Sklici
-0.69
psycopg
-0.62
heapq
-0.62
Shakspeare
-0.62
begrij
-0.61
vergeten
-0.59
bevestig
-0.58
POSITIVE LOGITS
monaster
0.79
ideolog
0.76
OVER
0.74
over
0.73
Over
0.70
utop
0.69
Over
0.65
republi
0.64
<bos>
0.63
conflic
0.61
Activations Density 0.073%