INDEX
Explanations
occurrences of the letter 'T' in various contexts
New Auto-Interp
Negative Logits
ſever
-1.01
་་
-0.96
Theſe
-0.95
Anſ
-0.93
Beſ
-0.93
iſt
-0.92
―――――
-0.92
ſelf
-0.91
ſelves
-0.90
leſs
-0.88
POSITIVE LOGITS
T
2.97
T
2.67
t
1.96
getT
1.78
Т
1.48
Т
1.40
T
1.33
t
1.32
ت
1.24
nT
1.20
Activations Density 0.092%