INDEX
Explanations
mentions of the name "Liz" and variations of it
New Auto-Interp
Negative Logits
exampleInputEmail
-0.15
aney
-0.15
tu
-0.14
ÑĪе
-0.14
Barg
-0.14
erus
-0.14
örü
-0.14
illy
-0.14
ivent
-0.14
owers
-0.13
POSITIVE LOGITS
beth
0.28
bon
0.25
boa
0.24
pector
0.23
zt
0.21
andro
0.20
osomal
0.20
burn
0.20
à¥įबन
0.19
osomes
0.18
Activations Density 0.011%