INDEX
Explanations
references to the name "Nik" in various contexts
New Auto-Interp
Negative Logits
acht
-0.21
eft
-0.17
eger
-0.16
idi
-0.16
occo
-0.15
ascar
-0.14
egra
-0.14
emplate
-0.14
atics
-0.14
quette
-0.14
POSITIVE LOGITS
laus
0.31
hil
0.28
olas
0.28
las
0.27
ita
0.26
itas
0.23
ko
0.22
ky
0.22
o
0.22
olet
0.21
Activations Density 0.006%