INDEX
Explanations
proper nouns related to a specific location, specifically "Jefferson City."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
789
+0.10
0.3%
486
+0.10
0.3%
1276
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
789
+0.10
0.03
216
+0.10
0.02
1120
+0.10
0.02
Negative Logits
betrays
-0.67
renounced
-0.66
strove
-0.64
forbade
-0.64
overtook
-0.63
swore
-0.60
endow
-0.60
darted
-0.59
abolish
-0.59
USTAIN
-0.59
POSITIVE LOGITS
Jefferson
2.65
Jefferson
2.48
Settembre
1.30
Ottobre
1.28
Luglio
1.20
Khart
1.17
palio
1.16
Giugno
1.14
saar
1.13
artig
1.10
Activations Density 0.183%