INDEX

Explanations

states of being or people

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

 altre

-1.44

為に

-1.41

 cuatro

-1.41

 momentous

-1.41

ごとの

-1.40

 semelh

-1.39

凄く

-1.38

ons

-1.38

 crucial

-1.38

きち

-1.34

POSITIVE LOGITS

 ones

1.77

who

1.66

 those

1.48

 should

1.46

 have

1.46

 people

1.37

院長

1.34

 continuously

1.31

one

1.30

Those

1.30

Activations Density 0.032%