INDEX
Explanations
the word "whatever" and phrases containing the word "whatever."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
699
+0.12
0.4%
2036
+0.11
0.4%
605
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2036
+0.12
0.03
699
+0.11
0.03
1801
+0.11
0.03
Negative Logits
Yess
-0.54
McLaugh
-0.54
Jusqu
-0.51
vecteur
-0.51
électron
-0.51
Daven
-0.51
Pon
-0.50
clô
-0.50
Lorsqu
-0.50
Pon
-0.48
POSITIVE LOGITS
whatever
0.92
sement
0.82
Whatever
0.79
whatever
0.78
whoever
0.78
Whatever
0.77
whichever
0.76
lele
0.74
loto
0.73
bander
0.71
Activations Density 0.067%