INDEX

Explanations

Code-related

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

#+#

-0.68

tvguidetime

-0.65

 onCancelled

-0.64

 Sarm

-0.57

رشف

-0.56

Hentet

-0.56

ⓘ

-0.56

kuuta

-0.56

 باسم

-0.53

AndEndTag

-0.53

POSITIVE LOGITS

parseDouble

0.57

 Control

0.55

 control

0.51

 contrôler

0.49

Control

0.49

 Controlling

0.47

RouterModule

0.46

ynchronously

0.46

ModelSerializer

0.45

ruptedException

0.45

Activations Density 0.003%