INDEX

Explanations

high quality/performance/grade

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

in

-1.73

to

-1.56

for

-1.55

by

-1.52

がありますが

-1.42

yship

-1.35

二郎

-1.34

it

-1.31

 them

-1.30

癖

-1.22

POSITIVE LOGITS

ฌ

1.16

dagog

1.13

ｒ

1.09

゚

1.08

為に

1.08

Etimología

1.07

 provenant

1.05

Universidad

1.04

 universale

1.03

 étudier

1.03

Activations Density 0.002%