INDEX

Explanations

data movement and destination

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

 noiva

-1.20

backslash

-1.16

 vantagem

-1.13

rceil

-1.13

をします

-1.08

 fazenda

-1.06

 caminhada

-1.04

 muun

-1.03

 CURIAM

-1.02

and

-1.01

POSITIVE LOGITS

 from

2.59

of

1.56

to

1.48

in

1.42

 into

1.22

 albeit

1.21

 applicazioni

1.15

 nuove

1.14

publicain

1.11

客气

1.10

Activations Density 0.110%