INDEX
Explanations
the name 'Ivan' in various contexts
New Auto-Interp
Negative Logits
ihan
-0.16
aul
-0.16
ebek
-0.15
tin
-0.15
epad
-0.15
enville
-0.15
inness
-0.15
gebung
-0.14
ebb
-0.14
Ïĩι
-0.14
POSITIVE LOGITS
hoe
0.37
ildo
0.23
ov
0.18
essian
0.17
ovna
0.17
oe
0.16
oodle
0.16
ovation
0.15
ishment
0.15
ilda
0.15
Activations Density 0.004%