INDEX

Explanations

time intervals and durations

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

喏

-1.23

 모든

-1.15

そういう

-1.09

什么呢

-1.07

uttgart

-1.06

 링크

-1.05

期刊论文

-1.05

 cathédrale

-1.04

獷

-1.03

 всі

-1.01

POSITIVE LOGITS

of

2.31

imee

1.33

the

1.28

 perquè

1.27

 that

1.22

 maaaring

1.22

сол

1.17

гами

1.16

 which

1.15

it

1.14

Activations Density 0.065%