INDEX

Explanations

personal pronouns and 'your'

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

by

-1.90

-1.55

ieR

-1.42

esomeness

-1.30

madonna

-1.29

 этим

-1.29

鴣

-1.28

tesse

-1.26

two

-1.25

 small

-1.25

POSITIVE LOGITS

vertible

1.41

 lección

1.38

ant

1.36

܆

1.34

 larmes

1.34

te

1.32

 huile

1.30

 entanto

1.30

durante

1.28

Activations Density 0.095%