INDEX
Explanations
locations of animal shelters and welfare organizations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
764
+0.36
1.4%
184
+0.33
1.3%
674
+0.25
1.0%
Correlated Neurons
Index
P. Corr.
Cos Sim.
764
+0.36
0.02
184
+0.33
0.01
1343
+0.25
0.01
Negative Logits
Bengt
-0.67
§.
-0.64
Olof
-0.62
Theile
-0.60
„,
-0.58
Karsten
-0.57
Thos
-0.57
Shakspeare
-0.56
Schäfer
-0.56
Nicolai
-0.56
POSITIVE LOGITS
<bos>
0.90
jajaja
0.60
IsContent
0.59
Lmfao
0.54
Chwiliwch
0.54
susun
0.54
<?
0.53
rrggbb
0.52
Hahah
0.50
springfox
0.49
Activations Density 0.022%