INDEX
Explanations
mentions of a particular person or establishment in news articles and social media posts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1013
+0.17
0.5%
1042
+0.11
0.3%
1533
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1347
+0.17
0.05
1533
+0.11
0.01
1013
+0.11
0.07
Negative Logits
heapq
-1.08
pymysql
-1.08
Præ
-1.03
pessi
-1.01
emphat
-0.99
abnorm
-0.98
smtplib
-0.97
wien
-0.97
Godt
-0.96
stockholm
-0.96
POSITIVE LOGITS
<bos>
1.04
business
0.74
customers
0.73
owner
0.67
shop
0.65
owners
0.64
staff
0.63
customer
0.62
location
0.62
employees
0.62
Activations Density 0.874%