INDEX

Explanations

the word "it" referring to a previous topic

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

::{

-0.58

 folha

-0.58

я

-0.55

RegistryLite

-0.52

 considérons

-0.50

 wijze

-0.48

-0.47

 casó

-0.46

 fullt

-0.45

POSITIVE LOGITS

 Majefty

1.19

Efq

1.16

 Theſe

1.15

 Reſ

1.11

 Monfieur

1.10

 purpoſe

1.06

 himſelf

1.02

 whoſe

0.98

 neceffary

0.98

 ſeveral

0.96

Activations Density 0.063%