INDEX

Explanations

words related to the propagation of information in simulations or other systems

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

 grise

-0.68

Etr

-0.68

 saks

-0.66

 topaz

-0.64

 meringue

-0.63

 súb

-0.63

素

-0.62

 alfab

-0.62

 pouce

-0.62

 Otra

-0.61

POSITIVE LOGITS

 propag

1.36

 Propag

1.16

propag

1.13

rungsseite

1.10

 propagate

1.09

 Propagation

1.07

 propagation

1.06

 propagating

1.01

oredCriteria

0.94

 propagated

0.94

Activations Density 0.003%