INDEX

Explanations

date or list items appearing

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

 both

-1.34

for

-1.27

 this

-1.23

on

-1.21

any

-1.11

 while

-1.05

家は

-1.01

 eight

-1.00

 until

-1.00

 exuberant

-1.00

POSITIVE LOGITS

 теперь

1.27

 executar

1.21

 élar

1.19

ඍ

1.12

beria

1.10

 Dinas

1.08

 magnific

1.08

dillos

1.07

 pensamientos

1.05

 ahora

1.04

Activations Density 0.000%