INDEX
Explanations
mentions of the name "Nick."
New Auto-Interp
Negative Logits
ansom
-0.16
-thirds
-0.15
zer
-0.15
ality
-0.15
Äĥr
-0.15
ufe
-0.15
uilder
-0.15
ÌĨ
-0.15
iram
-0.14
Detected
-0.14
POSITIVE LOGITS
laus
0.19
apult
0.17
eters
0.15
rng
0.15
lash
0.15
ombo
0.15
paces
0.14
eper
0.14
named
0.14
sei
0.14
Activations Density 0.011%