INDEX

Explanations

code tokens related to programming syntax and structure

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

 myſelf

-0.95

 itſelf

-0.86

 themſelves

-0.80

ViewFeatures

-0.73

+#+#

-0.71

 himſelf

-0.68

 raiſ

-0.68

 AssemblyCompany

-0.68

 Reſ

-0.67

 Monfieur

-0.66

POSITIVE LOGITS

testcase

0.55

seye

0.48

fromnode

0.48

mak

0.46

 tabindex

0.44

delt

0.44

urtstag

0.44

%{

0.43

engelsk

0.43

quan

0.42

Activations Density 0.706%