INDEX

Explanations

place names appearing in text

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

-1.62

 compleanno

-1.48

 Bewußt

-1.45

lysm

-1.44

 ormai

-1.36

 ۱۴۰۰

-1.33

 personaggio

-1.30

 Einfluß

-1.30

uiente

-1.29

isée

-1.29

POSITIVE LOGITS

to

2.03

 where

1.92

???:

1.38

but

1.36

🔙

1.27

uterte

1.26

auda

1.24

gilet

1.23

🫶

1.21

 régionale

1.20

Activations Density 0.333%