INDEX
Explanations
sentences ending with a period
sentences that end with a period
New Auto-Interp
Negative Logits
apers
-0.76
aper
-0.76
asers
-0.70
azo
-0.69
iquette
-0.69
anooga
-0.66
gger
-0.66
gradation
-0.65
graded
-0.64
robat
-0.64
POSITIVE LOGITS
[/
0.86
["
0.84
pg
0.80
<|endoftext|>
0.80
âĢķ
0.75
Adds
0.74
Lastly
0.72
[/
0.71
recalls
0.71
SHIP
0.71
Activations Density 0.099%