INDEX

Explanations

function arguments and parameters

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

 aéro

-1.32

engaged

-1.30

 meilleures

-1.30

雠

-1.26

apart

-1.23

崀

-1.23

theres

-1.22

attended

-1.22

 lié

-1.20

hey

-1.19

POSITIVE LOGITS

and

2.09

 then

1.59

 without

1.50

or

1.43

all

1.30

 have

1.29

 from

1.27

 until

1.25

not

1.23

 also

1.23

Activations Density 0.025%