INDEX
Explanations
phrases related to gluten-free products or recipes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.08
0.3%
1233
+0.07
0.3%
1224
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1233
+0.08
0.04
1224
+0.07
0.03
1736
+0.06
0.04
Negative Logits
<bos>
-0.94
/**
-0.67
/**
-0.63
invade
-0.62
<!--
-0.62
impeach
-0.62
/***
-0.61
plead
-0.61
consolidate
-0.60
collaborate
-0.59
POSITIVE LOGITS
Pyrene
1.03
Minang
1.03
riviera
0.99
bandung
0.99
soulign
0.98
véhic
0.95
Confu
0.94
eiffel
0.94
Momb
0.94
Sarm
0.94
Activations Density 0.103%