INDEX
Explanations
occurrences of the name "Kathryn" in various forms
New Auto-Interp
Negative Logits
še
-0.15
etta
-0.15
ted
-0.15
ova
-0.15
PEG
-0.14
ovic
-0.14
ptom
-0.14
owed
-0.14
igma
-0.14
tam
-0.14
POSITIVE LOGITS
mand
0.31
arine
0.26
MAND
0.25
leen
0.23
ryn
0.22
ery
0.18
rine
0.18
ires
0.18
olie
0.17
RY
0.17
Activations Density 0.008%