INDEX
Explanations
Scandinavian characters "Ã¥" and related phrases
the presence of the character "å" in various contexts
New Auto-Interp
Negative Logits
icity
-0.76
iazep
-0.71
uality
-0.69
aires
-0.66
iate
-0.65
iation
-0.64
interests
-0.64
arily
-0.63
idepress
-0.63
orial
-0.62
POSITIVE LOGITS
ð
0.96
ringe
0.86
los
0.85
hl
0.83
rn
0.83
lde
0.83
rd
0.80
tten
0.76
sb
0.76
rg
0.75
Activations Density 0.050%