INDEX

Explanations

commas followed by 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

 what

-1.80

one

-1.62

 both

-1.55

 Their

-1.44

 заметил

-1.35

 видит

-1.33

 resulting

-1.30

 result

-1.29

นาด

-1.28

 видел

-1.27

POSITIVE LOGITS

ของ

1.80

 этого

1.69

 этой

1.60

1.48

⩽

1.42

 của

1.40

 disfrute

1.40

 остальные

1.38

tahui

1.36

≳

1.34

Activations Density 0.102%