INDEX
Explanations
entities related to philanthropy and charity
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1129
+0.11
0.3%
282
+0.10
0.3%
1948
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1129
+0.11
0.06
282
+0.10
0.04
592
+0.09
0.01
Negative Logits
disreg
-1.24
hairc
-1.07
intersper
-1.06
Hahah
-1.04
indestru
-0.98
encomp
-0.97
Hahahahaha
-0.97
Lmfao
-0.97
cytoplas
-0.95
broderie
-0.95
POSITIVE LOGITS
charitable
1.00
charity
0.97
charities
0.97
philanthropic
0.92
donations
0.92
philanthropy
0.87
nonprofit
0.86
donation
0.84
Donations
0.79
Charities
0.78
Activations Density 0.693%