INDEX

Explanations

all things or everything

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

todos

-0.93



-0.75

avait

-0.75

гъл

-0.75

setResult

-0.74

 entidade

-0.74

 sappi

-0.72

 zoon

-0.72

criter

-0.72

habited

-0.71

POSITIVE LOGITS

 things

1.88

 Things

1.27

things

1.23

 thing

1.21

Things

1.18

 everything

1.15

ALL

1.11

 вещи

1.09

 THINGS

1.07

 Everything

1.06

Activations Density 0.008%