INDEX

Explanations

mention what, prove you, highlight these

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

Only

-1.22

<bos>

-1.21

 jedynie

-1.20

 pouze

-1.20

 между

-1.18

 only

-1.16

 тільки

-1.16

 mediodía

-1.15

only

-1.15

 только

-1.14

POSITIVE LOGITS

 your

2.03

 then

1.34

any

1.34

 yourself

1.26

 with

1.25

ığınız

1.24

 when

1.19

valida

1.16

ar

1.13

 using

1.13

Activations Density 0.167%