INDEX

Explanations

to

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

 document

-0.51

 Document

-0.47

gl

-0.46

 documentation

-0.46

mo

-0.46

Mud

-0.46

 take

-0.45

esModule

-0.45

oter

-0.45

bas

-0.45

POSITIVE LOGITS

 nôtre

0.81

 étoit

0.75

 enfans

0.74

 feroit

0.71

 pouvoit

0.71

 supérieures

0.71

 mourut

0.69

 suivants

0.69

 auroit

0.68

 actuels

0.68

Activations Density 0.001%