INDEX

Explanations

countries and regions

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

 then

-1.26

it

-1.25

 близь

-1.22

既然

-1.20

 problemi

-1.18

 have

-1.18

ctives

-1.16

K

-1.16

ﻄ

-1.15

to

-1.13

POSITIVE LOGITS

1.28

.},

1.23

who

1.21

 they

1.20

 orgánica

1.18

畠

1.16

who

1.16

体型

1.16

ってください

1.16

1.13

Activations Density 0.083%