INDEX

Explanations

code and documentation

hexadecimal strings and alphanumeric identifiers in technical code and documentation.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 outcome

-1.52

 sababu

-1.47

をしました

-1.46

 kwamba

-1.41

笑了笑

-1.40

 this

-1.38

 again

-1.34

angerie

-1.34

 komplet

-1.27

 hivyo

-1.27

POSITIVE LOGITS

but

1.66

шных

1.49

 словом

1.45

 will

1.44

and

1.40

 with

1.38

 яйцо

1.34

انجليز

1.30

 作り方

1.29

кож

1.27

Activations Density 0.025%