INDEX

Explanations

code structure and programming context

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

and

-1.11

...

-1.00

-0.96

 there

-0.93

 There

-0.91

に着

-0.91

--

-0.90

して下さい

-0.89

....

-0.87

...............

-0.87

POSITIVE LOGITS

 manquer

1.20

pewa

1.16

 paragraphe

1.09

 espé

1.08

 reager

1.05

 gånger

1.04

 linge

1.04

Precis

1.02

 bekym

1.02

Koko

1.01

Activations Density 0.018%