INDEX
Explanations
phrases related to pets or animals
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1677
+0.16
0.7%
1339
+0.16
0.7%
553
+0.13
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1677
+0.16
0.03
1335
+0.16
0.03
553
+0.13
0.02
Negative Logits
rafas
-0.48
bivolt
-0.44
ナソニック
-0.44
zköz
-0.43
uttosto
-0.42
ureusement
-0.42
ௌ
-0.42
pendenti
-0.42
knap
-0.42
capaian
-0.41
POSITIVE LOGITS
Pet
1.35
Pet
1.35
pet
1.29
pet
1.29
PET
1.20
PET
1.11
pets
1.09
Pets
1.06
pets
1.05
Pets
1.02
Activations Density 0.090%