INDEX
Explanations
the verb "is" in various contexts
New Auto-Interp
Negative Logits
uns
-0.15
omm
-0.15
older
-0.14
edges
-0.14
379
-0.14
.yahoo
-0.14
essa
-0.13
aken
-0.13
esso
-0.13
Ñħи
-0.13
POSITIVE LOGITS
ÌĨ
0.17
̧
0.15
SplitOptions
0.15
issen
0.14
plx
0.14
tÃŃ
0.14
tmpl
0.14
’na
0.14
mlink
0.14
/do
0.14
Activations Density 0.577%