INDEX

Explanations

arises from, might be

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

niers

2.42

ினா

2.33

ье

2.29

cısı

2.28

ujem

2.25

 Meir

2.25

NA

2.22

ὕ

2.19

TAINS

2.17

یں

2.16

POSITIVE LOGITS

 Fixed

2.41

此之外

2.31

titleMargin

2.22

 დას

2.20

}{{

2.18

\]

2.17

၉

2.16

ي

2.13

alek

2.12

 ალ

2.09

Activations Density 0.002%