INDEX

Explanations

thanks and support

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

 after

-1.10

as

-1.05

 when

-0.95

by

-0.94

on

-0.92

 because

-0.91

if

-0.90

ähkö

-0.89

vestido

-0.89

laund

-0.89

POSITIVE LOGITS

 thanks

1.50

 Thanks

1.45

 support

1.42

 grateful

1.40

 funding

1.37

 thanked

1.27

 soutien

1.27

 gratitude

1.23

 assistance

1.21

 supporto

1.17

Activations Density 0.017%