INDEX

Explanations

suits and tailoring

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

 leggings

-0.81

 tiara

-0.80

eval

-0.73

鷥

-0.73

 gruppi

-0.73

DP

-0.73

unzel

-0.73

rieks

-0.71

 evaluations

-0.71

 eval

-0.71

POSITIVE LOGITS

 suit

1.73

 suits

1.56

 Suit

1.36

 tailoring

1.36

 tailor

1.30

 bespoke

1.24

 bouton

1.20

Suit

1.20

 Suits

1.18

 tailored

1.17

Activations Density 0.019%