INDEX
Explanations
instances of the word "then" in various contexts
New Auto-Interp
Negative Logits
Harlow
-0.76
Vip
-0.72
Folsom
-0.72
Irm
-0.70
лися
-0.69
fap
-0.69
checkNotNull
-0.69
himſelf
-0.69
Marge
-0.67
Newsom
-0.67
POSITIVE LOGITS
THEN
1.53
then
1.51
THEN
1.43
Then
1.40
then
1.33
Then
1.29
entonces
1.10
Entonces
1.09
dann
1.05
Dann
1.05
Activations Density 0.084%