INDEX

Explanations

code context

boolean logic symbols and keywords.

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

Negative Logits

<bos>

-0.56

路

-0.47

<0xE8>

-0.41

間

-0.40

ٔ

-0.39

rå

-0.39

ad

-0.38

PDOException

-0.38

bri

-0.38

componentDid

-0.38

POSITIVE LOGITS

 themſelves

0.81

 myſelf

0.80

 MainAxisSize

0.73

 Theſe

0.73

 himſelf

0.73

 pleaſure

0.71

 Jefus

0.68

enderror

0.68

 juſ

0.67

 للاسماء

0.66

Activations Density 0.862%