INDEX
Explanations
instances of the verb "show" in various contexts
New Auto-Interp
Negative Logits
Brito
-0.88
Balt
-0.77
esenciales
-0.76
lápiz
-0.75
Spacing
-0.72
••••
-0.65
solitario
-0.64
Petra
-0.64
pakt
-0.64
zünd
-0.64
POSITIVE LOGITS
Shows
1.69
shows
1.65
Shows
1.61
shows
1.60
SHOW
1.58
SHOW
1.58
SHOWING
1.58
SHOWS
1.52
Showing
1.51
showed
1.49
Activations Density 0.150%