INDEX

Explanations

documentation comments

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

ছে

-1.47

ются

-1.30

-1.27

its

-1.24

 bambú

-1.23

 Saltar

-1.18

 nombreuses

-1.16

𝟐

-1.16

数百

-1.16

 certaines

-1.16

POSITIVE LOGITS

who

2.31

 where

1.44

 since

1.42

 when

1.32

 berbeda

1.30

on

1.28

if

1.27

ні

1.27

unggah

1.26

 विश्वसनीयता

1.26

Activations Density 0.004%