INDEX
Explanations
references to specific names or terms containing the letters 'br'
occurrences of the substring "br" in various contexts
New Auto-Interp
Negative Logits
eers
-0.92
STER
-0.83
AMERICA
-0.76
WARE
-0.71
WARN
-0.67
ographed
-0.65
Samoa
-0.64
requires
-0.64
DEBUG
-0.63
Totem
-0.63
POSITIVE LOGITS
ackets
1.13
acket
1.07
igham
1.07
ushed
0.95
ighter
0.95
anches
0.94
ainer
0.92
idget
0.92
acing
0.89
ained
0.88
Activations Density 0.008%