INDEX
Explanations
mentions of marijuana-related terms and topics
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1742
+0.13
0.4%
1406
+0.12
0.4%
1306
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1742
+0.13
0.04
1406
+0.12
0.04
1306
+0.11
0.04
Negative Logits
Sklici
-0.63
///</
-0.57
Przyp
-0.55
@[+][
-0.54
externi
-0.54
DeleteBehavior
-0.53
település
-0.53
municipi
-0.52
StoreMessageInfo
-0.52
spesies
-0.51
POSITIVE LOGITS
marijuana
1.07
Marijuana
0.97
cannabis
0.91
juana
0.89
Cannabis
0.82
Cannabis
0.78
cannabis
0.72
weed
0.62
THC
0.58
pot
0.57
Activations Density 0.088%