INDEX

Explanations

similes using the words "like" or "as".

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UserScript

-0.82

EndContext

-0.81

BeginContext

-0.80

SupportActionBar

-0.73

didSet

-0.71

fromnode

-0.70

StructEnd

-0.69

 AssemblyProduct

-0.68

UrlResolution

-0.68

GEBURTSDATUM

-0.68

POSITIVE LOGITS

 like

0.51

0.50

 Like

0.48

Like

0.47

 fast

0.45

ผ

0.43

like

0.43

fast

0.43

vol

0.42

zan

0.42

Activations Density 0.042%