INDEX
Explanations
cultural elements related to hip-hop music
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
251
+0.13
0.5%
1034
+0.12
0.5%
1758
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1331
+0.13
0.03
1557
+0.12
0.02
1758
+0.12
0.02
Negative Logits
viders
-0.60
alions
-0.53
astéro
-0.53
Skład
-0.50
Mulberry
-0.50
Cechy
-0.49
Dzięki
-0.49
atients
-0.49
Warto
-0.49
Pozdrawiam
-0.48
POSITIVE LOGITS
hip
1.46
Hip
1.42
Hip
1.33
HIP
1.14
rap
1.03
hip
1.02
hips
0.99
HIP
0.94
Rap
0.92
Rap
0.90
Activations Density 0.105%