INDEX

Explanations

names followed by surnames or initials

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

-4.03

</strong>

-2.44

 nových

-2.38

増えて

-2.34

 lepší

-2.31

Ꝑ

-2.31

渽

-2.28

 něj

-2.27

ходит

-2.22

 těch

-2.13

POSITIVE LOGITS

 einige

2.73

from

2.61

ā

2.38

Our

2.34

dată

2.34

 Then

2.33

 zahlreiche

2.25

While

2.23

 из

2.20

 από

2.19

Activations Density 0.025%