INDEX
Explanations
phrases related to business negotiations and layoffs
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
764
+0.20
0.7%
184
+0.15
0.5%
1499
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
184
+0.20
0.02
1904
+0.15
0.03
939
+0.11
0.03
Negative Logits
indeb
-0.98
solidar
-0.96
gesta
-0.95
anse
-0.93
utop
-0.93
<bos>
-0.91
interag
-0.85
broder
-0.83
lapto
-0.83
venez
-0.81
POSITIVE LOGITS
pamph
1.21
Shakspeare
1.14
McLaugh
1.13
Whence
1.09
unspeak
1.03
Confu
1.03
barbarous
1.02
McInt
1.02
despotism
1.01
Bartholo
0.99
Activations Density 0.139%