INDEX

Explanations

code

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

 CreateTagHelper

-0.73

principalTable

-0.68

 AssemblyCompany

-0.66

 autorytatywna

-0.63

DeleteBehavior

-0.62

 שוליים

-0.58

 مشين

-0.57

onoi

-0.57

entgen

-0.56

-0.52

POSITIVE LOGITS

fører

0.45

MITTED

0.44

speak

0.44

thoven

0.44

لاعات

0.44

nima

0.44

 Himo

0.44

än

0.44

NÍ

0.44

 Verfügung

0.43

Activations Density 0.023%