food items in wraps or balls

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

-1.35

 kaplama

-1.33

-1.27

-1.24

-1.20

kanı

-1.19

’

-1.16

 дож

-1.16

POSITIVE LOGITS

<bos>

1.42

щення

1.41

 agradec

1.38

걀

1.31

()])

1.30

arci

1.26

ництво

1.24

焄

1.23

liese

1.23

ikbaar

1.23

Activations Density 0.015%