INDEX

Explanations

return or coming back

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

-1.16

老头

-1.14

悩む

-1.12

 amables

-1.09

-1.07

 şimdi

-1.05

 ermöglich

-1.04

-1.02

-1.00

uzes

-0.99

POSITIVE LOGITS

 from

2.80

 pulang

1.59

Returned

1.50

 Returned

1.49

 return

1.46

 returned

1.44

 Returning

1.40

 after

1.40

 returning

1.35

回来

1.34

Activations Density 0.020%