INDEX
Explanations
mentions of the name "David" in various contexts
New Auto-Interp
Negative Logits
ihan
-0.18
cret
-0.16
ë
-0.15
eyin
-0.15
pector
-0.15
kick
-0.14
eru
-0.14
iversit
-0.14
itia
-0.14
../../../
-0.13
POSITIVE LOGITS
son
0.17
aceous
0.16
/or
0.15
sonian
0.15
SON
0.15
774
0.15
lyn
0.14
zimmer
0.14
ccione
0.14
ancell
0.14
Activations Density 0.029%