INDEX

Explanations

end of sentence marker

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

 also

-1.34

 will

-1.21

 diesen

-1.02

はこの

-1.00

 также

-0.99

 such

-0.98

此外

-0.98

这样的

-0.97

 exempel

-0.97

 nawet

-0.96

POSITIVE LOGITS

 again

1.40

に行きました

1.14

 then

1.13

 Again

1.10

 opět

1.08

榎

1.06

 novamente

1.05

unächst

1.04

 entonces

1.02

 erneut

1.02

Activations Density 0.017%