INDEX

Explanations

words starting with Ad

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

vantaged

-4.66

 trough

-3.28

juvant

-2.64

 also

-2.63

.’’

-2.52

 quatrième

-2.50

,’’

-2.39

 accompanied

-2.36

なども

-2.30

嵛

-2.25

POSITIVE LOGITS

↵↵

2.92

状况

2.73

ୈ

2.72

疍

2.70

you

2.45

栳

2.44

鰱

2.42

攆

2.42

躂

2.42

狆

2.31

Activations Density 0.053%