INDEX

Explanations

numbers and letters like Z

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

,..

-1.37

いつも

-1.36

以前

-1.30

,.

-1.30

 прош

-1.30

 segurando

-1.29

 این

-1.28

去年

-1.26

assumed

-1.24

 specif

-1.23

POSITIVE LOGITS

 with

2.30

 from

1.94

out

1.48

for

1.42

in

1.36

 through

1.32

by

1.32

or

1.29

at

1.26

 znamen

1.23

Activations Density 0.037%