INDEX
Explanations
phrases related to crime and law enforcement
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1042
+0.09
0.3%
1978
+0.09
0.2%
1445
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2030
+0.09
0.04
1839
+0.09
0.06
1519
+0.07
0.04
Negative Logits
pymysql
-0.92
getty
-0.79
contex
-0.78
hcm
-0.75
smtplib
-0.73
psycopg
-0.73
volunte
-0.73
stockholm
-0.72
ipo
-0.72
seoul
-0.72
POSITIVE LOGITS
we
0.82
you
0.79
they
0.78
she
0.69
he
0.66
jakie
0.64
available
0.64
that
0.62
required
0.60
offered
0.60
Activations Density 0.387%