INDEX
Explanations
references to the word "slim" in various contexts
New Auto-Interp
Negative Logits
stall
-0.17
allis
-0.15
heim
-0.15
iol
-0.14
nid
-0.14
asjon
-0.14
stunt
-0.14
result
-0.14
zá
-0.13
gan
-0.13
POSITIVE LOGITS
sonian
0.17
UDGE
0.15
essaging
0.15
áce
0.15
TINGS
0.15
0.15
otta
0.15
ady
0.14
arez
0.14
pector
0.14
Activations Density 0.003%