INDEX

Explanations

technical text

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

 Race

-0.48

Académie

-0.46

 "..\..\

-0.45

Race

-0.44

 race

-0.44

 Infórmanos

-0.43

 legais

-0.42

 ErrIntOverflow

-0.42

OPS

-0.41

➟

-0.41

POSITIVE LOGITS

CodeAttribute

0.69

PullParser

0.63

NameInMap

0.62

LabelTagHelper

0.60

SequentialGroup

0.59

Cyfarwyddwr

0.58

orem

0.57

 estekak

0.56

CompleteListener

0.56

writeFieldEnd

0.56

Activations Density 0.001%