INDEX

Explanations

affirmation or certainty

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

 этими

-2.55

떳

-2.48

 hinder

-2.44

()}

-2.41

 люди

-2.33

 perilous

-2.33

$\

-2.30

these

-2.28

ৢ

-2.28

 много

-2.25

POSITIVE LOGITS

that

2.61

 concluding

2.23

و

2.20

 kela

2.13

ور

2.09

ت

2.05

2.00

т

2.00

 rosse

1.98

 kropp

1.95

Activations Density 0.022%