INDEX
Explanations
phrases related to polyamory and relationship dynamics
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1622
+0.17
0.7%
1520
+0.12
0.5%
1387
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1622
+0.17
0.02
689
+0.12
0.02
120
+0.12
0.02
Negative Logits
Kriege
-0.46
TargetException
-0.44
BRACKET
-0.43
carboxylic
-0.42
Erbe
-0.42
meiras
-0.42
乓
-0.42
سكانية
-0.42
Dingen
-0.41
ביותר
-0.41
POSITIVE LOGITS
poly
1.40
Poly
1.39
poly
1.36
Poly
1.35
POLY
1.15
POLY
1.13
polyg
1.05
poli
0.87
polig
0.86
polyps
0.82
Activations Density 0.082%