INDEX
Explanations
references to sheets, particularly in the context of bedding or laundry
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
376
+0.17
1.0%
156
+0.15
0.9%
306
+0.13
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
306
+0.17
0.01
19
+0.15
0.01
198
+0.13
0.01
Negative Logits
yours
-2.14
choosing
-1.74
vain
-1.68
somebody
-1.61
rian
-1.58
fancy
-1.53
your
-1.52
groups
-1.50
Walt
-1.49
dreams
-1.48
POSITIVE LOGITS
ĻĤ
2.30
ģ
2.26
80211
1.95
ball
1.91
dimen
1.82
uve
1.81
Ī
1.77
iom
1.77
eto
1.76
heet
1.72
Activations Density 0.014%