INDEX

Explanations

mentions of the word "dit" with varying confidence levels

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewFeatures

-0.88

 nakalista

-0.87

IsMutable

-0.79

Hentet

-0.79

ToRefresh

-0.79

enumi

-0.76

UnusedPrivate

-0.76

:✨

-0.75

 Monfieur

-0.73

 obſ

-0.73

POSITIVE LOGITS

dit

3.33

Dit

2.14

Dit

2.06

 ditch

1.71

dit

1.70

 ditches

1.44

ditch

1.28

 Ditch

1.20

DIT

1.20

 dite

1.13

Activations Density 0.001%