INDEX
Explanations
text related to returning or looking forward to specific events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1013
+0.12
0.3%
678
+0.11
0.3%
479
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
636
+0.12
0.03
1490
+0.11
0.03
1356
+0.10
0.02
Negative Logits
Février
-1.00
🤣🤣
-0.99
matel
-0.95
Décembre
-0.95
!...
-0.94
Lmfao
-0.93
Lmao
-0.93
Lma
-0.93
Wtf
-0.90
Ikr
-0.89
POSITIVE LOGITS
upcoming
0.60
betweenstory
0.54
next
0.53
Hauptartikel
0.52
someday
0.51
see
0.50
ccedil
0.49
GEBURTSDATUM
0.49
hopefully
0.48
seeing
0.48
Activations Density 0.174%