INDEX

Explanations

adverbs followed by descriptive words

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

of

-1.89

to

-1.79

着自己的

-1.30

type

-1.28

 part

-1.27

が悪い

-1.27

が上が

-1.27

ebly

-1.24

part

-1.23

aned

-1.23

POSITIVE LOGITS

 only

1.45

šinou

1.39

and

1.38

しております

1.35

 knew

1.35

Médaille

1.28

 could

1.28

 will

1.26

 always

1.23

那些

1.22

Activations Density 0.039%