INDEX
Explanations
information regarding news stories and video clips, including quotes and dates
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
906
+0.10
0.3%
678
+0.10
0.3%
615
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
615
+0.10
0.03
1309
+0.10
0.04
678
+0.09
0.05
Negative Logits
hunde
-0.67
bolí
-0.56
benzin
-0.55
masaj
-0.54
bunda
-0.53
portu
-0.53
meras
-0.53
sarili
-0.52
kulum
-0.52
]$}
-0.51
POSITIVE LOGITS
intersper
0.92
timelapse
0.89
youtube
0.88
resear
0.88
YouTube
0.86
video
0.85
Youtube
0.85
encomp
0.85
videos
0.83
vids
0.79
Activations Density 0.318%