INDEX

Explanations

purpose or reason

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

 capucha

-2.03

 empê

-1.94

 sudadera

-1.93

 renfer

-1.90

歺

-1.86

 sellado

-1.85

 acabados

-1.80

 embalaje

-1.78

 camiones

-1.77

 vrais

-1.77

POSITIVE LOGITS

to

7.19

for

5.94

 для

3.31

as

3.30

เพื่อ

2.89

 because

2.58

 untuk

2.47

 để

2.45

 برای

2.36

 чтобы

2.34

Activations Density 0.091%