INDEX

Explanations

references to past time

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

 porque

-1.53

 speciale

-1.46

 nuovo

-1.41

 nuov

-1.40

three

-1.39

睃

-1.35

歺

-1.35

 amortecedor

-1.34

穑

-1.34

actéristi

-1.34

POSITIVE LOGITS

1.84

or

1.52

 this

1.47

at

1.29

 píše

1.19

 time

1.16

 Andrew

1.13

グレード

1.09

is

1.08

 zeggen

1.08

Activations Density 0.124%