INDEX
Explanations
words related to technical computer activities like logging in, registering, and managing accounts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1276
+0.09
0.3%
946
+0.08
0.2%
120
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
284
+0.09
0.02
946
+0.08
0.02
482
+0.08
0.02
Negative Logits
userModel
-0.73
ApiService
-0.64
getCategory
-0.58
userRole
-0.56
getCity
-0.55
Obtener
-0.54
getCustomer
-0.54
romero
-0.53
rir
-0.52
Conexion
-0.51
POSITIVE LOGITS
login
1.09
Login
1.01
login
0.94
Login
0.86
LOGIN
0.80
LOGIN
0.70
username
0.70
Ename
0.68
logout
0.63
登录
0.61
Activations Density 0.100%