INDEX
Explanations
phrases related to political and social movements
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1105
+0.09
0.3%
138
+0.09
0.3%
406
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
138
+0.09
0.06
1297
+0.09
0.03
1105
+0.09
0.04
Negative Logits
pixabay
-0.72
unsplash
-0.67
shutterstock
-0.65
<bos>
-0.60
cushi
-0.59
¡¡
-0.59
GIPHY
-0.59
ecru
-0.58
gettyimages
-0.56
wikihow
-0.55
POSITIVE LOGITS
PreferredItem
0.48
Snowden
0.48
Бахар
0.48
Freih
0.47
клопе
0.46
Duisburg
0.46
pyram
0.45
Gouver
0.45
SEDS
0.44
Papst
0.44
Activations Density 0.335%