INDEX
Explanations
sentences ending with a period
punctuation marks, particularly periods and their frequency
New Auto-Interp
Negative Logits
enthusi
-0.70
bondage
-0.69
buggy
-0.68
battered
-0.66
traveler
-0.65
spr
-0.63
travelers
-0.63
shells
-0.62
exotic
-0.61
itiz
-0.61
POSITIVE LOGITS
70710
1.07
05
1.00
000000
0.99
003
0.98
0001
0.98
005
0.97
025
0.97
002
0.95
00000000
0.95
0000000000000000
0.95
Activations Density 0.048%