INDEX

Explanations

forbidden from discussing

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

 inch

2.40

ipy

2.34

ки

2.30

es

2.28

evich

2.27

 precious

2.25

ы

2.23

 implements

2.22

스럽

2.20

astype

2.19

POSITIVE LOGITS

ﮟ

2.48

 গ্রামের

2.24

 말이

2.23

ణి

2.15

ifical

2.14

 droite

2.13

وان

2.10

 aktivnosti

2.09

ậc

2.08

érateur

2.08

Activations Density 0.000%