INDEX

Explanations

the word "cleaved" or similar

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Normdatei

-0.95

 Alcott

-0.86

URLException

-0.85

 Nema

-0.84

 Мексичка

-0.83

SUE

-0.83

 Walpole

-0.79

 ProtoMessage

-0.79

 "..\..\

-0.79

Referencies

-0.78

POSITIVE LOGITS

Cle

1.53

cle

1.42

Cle

1.42

CLE

1.16

 cleavage

1.07

 Clemens

1.02

 cleave

0.99

cle

0.96

CLE

0.94

 Clements

0.90

Activations Density 0.005%