INDEX
Explanations
The neuron is looking for names of assorted people
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1177
+0.14
0.4%
1842
+0.11
0.3%
283
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1177
+0.14
0.04
1056
+0.11
0.07
283
+0.10
0.01
Negative Logits
userType
-0.67
userEmail
-0.65
колеп
-0.64
firebaseConfig
-0.63
postData
-0.58
OGND
-0.57
isAdmin
-0.57
loggedIn
-0.57
""){-0.56
mahd
-0.56
POSITIVE LOGITS
franz
0.89
mef
0.83
anton
0.81
dora
0.80
sven
0.79
cyr
0.75
angelo
0.74
Chapitre
0.74
Portail
0.72
trouva
0.71
Activations Density 0.346%