INDEX

Explanations

relational descriptions

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

 with

-1.80

၈

-1.25

၃

-1.20

 their

-1.14

＆

-1.13

 others

-1.13

and

-1.13

塹

-1.11

 czemu

-1.11

all

-1.09

POSITIVE LOGITS

 corriger

1.33

 accompagner

1.28

 soucis

1.25

 imprimer

1.25

 humeur

1.24

 douane

1.23

 verbe

1.21

 salade

1.19

 gela

1.18

 gese

1.15

Activations Density 0.177%