INDEX
Explanations
terms related to hops and corn in brewing contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1921
+0.21
1.1%
1983
+0.18
1.0%
650
+0.16
0.9%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1921
+0.21
0.03
1983
+0.18
0.02
650
+0.16
0.02
Negative Logits
<bos>
-1.33
FlatStyle
-0.84
SequentialGroup
-0.83
FlatAppearance
-0.80
/*
-0.73
-0.72
deck
-0.72
onAnimation
-0.72
الرياضيه
-0.71
Referències
-0.71
POSITIVE LOGITS
reluct
1.96
indestru
1.91
excru
1.83
maneu
1.83
disagre
1.83
increa
1.79
shenan
1.76
unspeak
1.76
apprehen
1.75
uninten
1.72
Activations Density 0.129%