INDEX
Explanations
references to a specific news organization, ABC News, and related terms
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1741
+0.14
0.5%
61
+0.14
0.5%
1222
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
61
+0.14
0.02
650
+0.14
0.02
420
+0.13
0.02
Negative Logits
Datuak
-0.68
Tikang
-0.54
willows
-0.51
linden
-0.51
GenerationType
-0.51
conifers
-0.47
ingrat
-0.47
boughs
-0.46
wurde
-0.46
solemnity
-0.46
POSITIVE LOGITS
ABC
1.38
ABC
1.29
abc
1.01
abc
1.00
Abc
0.79
ekos
0.76
Kategor
0.71
konserv
0.70
alkoh
0.68
akut
0.68
Activations Density 0.055%