INDEX
Explanations
sentences ending with a specific punctuation mark
sentences that end with a period
New Auto-Interp
Negative Logits
wcs
-0.84
etheless
-0.78
translation
-0.77
alysed
-0.74
ãĥĦ
-0.73
inarily
-0.68
romeda
-0.65
artifacts
-0.65
ihar
-0.65
isans
-0.64
POSITIVE LOGITS
Smith
1.01
Powell
0.98
Baker
0.96
Johnson
0.96
Robinson
0.95
Roberts
0.95
Schw
0.93
Hughes
0.93
Olson
0.90
Mellon
0.88
Activations Density 0.042%