INDEX

Explanations

questions and code snippets

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

of

-1.63

-1.41

较为

-1.32

でしたか

-1.29

 ihre

-1.23

paravant

-1.20

 jejich

-1.15

 crecer

-1.10

İyi

-1.10

ingresso

-1.09

POSITIVE LOGITS

 observa

1.44

 mischievous

1.37

 venezia

1.36

 identifica

1.31

 relata

1.26

viamo

1.26

 prepara

1.25

 archivio

1.25

"));

1.23

‌های

1.23

Activations Density 0.002%