INDEX

Explanations

What distinguishes features

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

nya

2.86

了

2.69

다면

2.68

्त

2.54

ts

2.33

्स

2.28

mi

2.27

اً

2.26

ların

2.24

्

2.21

POSITIVE LOGITS

<bos>

2.99

ِّف

2.39

⁢</

2.37

 PluginResult

2.36

 ModelAndView

2.36

Namara

2.31

فير

2.29

ന്വേഷ

2.27

ℙ

2.22

 খেলতে

2.21

Activations Density 0.065%