INDEX

Explanations

in

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rawDesc

-0.87

MigrationBuilder

-0.85

InjectAttribute

-0.84

windowFixed

-0.80

HasAnnotation

-0.79

writeFieldEnd

-0.78

 виправивши

-0.75



-0.75

 Places

-0.75

protoimpl

-0.75

POSITIVE LOGITS

lo

0.45

 quality

0.43

ez

0.43

set

0.42

zec

0.41

Lue

0.40

有

0.40

iez

0.40

 stad

0.39

Activations Density 0.002%