INDEX

Explanations

rarely used

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

 скром

-1.27

 représenter

-1.27

BEFORE

-1.25

 Шаг

-1.23

picable

-1.20

 hés

-1.17

 кровати

-1.17

鹟

-1.16

 betek

-1.16

 participer

-1.16

POSITIVE LOGITS

 then

1.55

 still

1.42

 there

1.34

if

1.30

 which

1.27

 unused

1.24

leta

1.23

 Equipment

1.22

If

1.21

Use

1.20

Activations Density 0.075%