INDEX
Explanations
references to the letter 'g' in varied forms and contexts
New Auto-Interp
Negative Logits
oland
-0.16
overs
-0.15
hierarchy
-0.15
xico
-0.15
bolt
-0.15
rij
-0.15
Lone
-0.15
nut
-0.14
overe
-0.14
Pru
-0.14
POSITIVE LOGITS
owns
0.34
own
0.30
lam
0.30
ingham
0.26
OWN
0.25
orgeous
0.23
lamaz
0.22
ORG
0.22
ucci
0.21
own
0.21
Activations Density 0.022%