INDEX
Explanations
the keyword "sc" at various positions in the text
New Auto-Interp
Negative Logits
elsen
-0.75
lapse
-0.71
remembrance
-0.71
nown
-0.67
terday
-0.64
emonic
-0.64
contender
-0.63
heit
-0.63
éĹĺ
-0.62
acknowledgement
-0.60
POSITIVE LOGITS
rupulous
1.39
oops
1.37
ammers
1.27
ouring
1.25
rawling
1.24
opes
1.20
atters
1.19
ribe
1.18
rawled
1.17
outed
1.15
Activations Density 0.009%