INDEX
Explanations
mentions of the brand "Apple."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.38
1.6%
184
+0.14
0.6%
1919
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1919
+0.38
0.10
1097
+0.14
0.09
1504
+0.12
0.06
Negative Logits
<bos>
-2.34
perla
-0.73
Seeder
-0.72
cristian
-0.72
adal
-0.72
solidar
-0.71
anse
-0.71
prostitu
-0.71
estimable
-0.69
augus
-0.69
POSITIVE LOGITS
pymysql
1.23
Wtf
1.05
unspeak
1.02
psycopg
0.98
Lmao
0.98
heapq
0.96
pymongo
0.93
idéale
0.92
affor
0.90
McLaugh
0.88
Activations Density 0.452%