INDEX

Explanations

numbers preceding or following prompts

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ւ

2.75

्याने

2.40

ภัณฑ์

2.39

ripción

2.25

memberNameLink

2.24

靂

2.22

etem

2.16

像是

2.12

ehle

2.12

bæ

2.11

POSITIVE LOGITS

боре

2.25

র

2.17

2.08

 heureux

2.08

rounds

2.04

িয়া

2.02

 huile

1.94

houn

1.92

ু

1.91

millis

1.91

Activations Density 0.124%