INDEX
Explanations
occurrences of the string "br" in the text
New Auto-Interp
Negative Logits
Essen
-0.50
cetines
-0.50
Doyle
-0.48
Futter
-0.45
rese
-0.45
ake
-0.45
ate
-0.44
《
-0.44
Allocate
-0.44
vale
-0.44
POSITIVE LOGITS
br
2.42
br
1.55
Br
1.52
BR
1.50
Br
1.47
BR
1.29
mbr
0.94
brk
0.88
brl
0.87
brin
0.85
Activations Density 0.005%