INDEX
Explanations
phrases related to veganism and animal cruelty
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1013
+0.12
0.4%
58
+0.11
0.3%
1741
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1307
+0.12
0.02
58
+0.11
0.01
1915
+0.11
0.02
Negative Logits
+#+#
-0.60
醐
-0.58
HtmlAttribute
-0.58
IsContent
-0.57
يتيمه
-0.57
intios
-0.56
DoubleQuotes
-0.56
LUMP
-0.55
للاسماء
-0.55
Economía
-0.55
POSITIVE LOGITS
vegan
1.10
Vegan
1.03
vegan
1.01
Vegan
1.00
vegans
0.94
suscep
0.93
McLaugh
0.92
reluct
0.92
unspeak
0.91
Thos
0.86
Activations Density 0.081%