INDEX

Explanations

names followed by a description

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

чя

-1.38

-1.23

薮

-1.21

franc

-1.13

мся

-1.05

祇

-1.04

vides

-1.02

of

-0.99

柘

-0.98

𝑣

-0.98

POSITIVE LOGITS

1.41

 большин

1.29

 what

1.25

InUse

1.25

logna

1.22

lenül

1.19

 interested

1.17

ސ

1.17

이스

1.17

стема

1.16

Activations Density 0.189%