INDEX

Explanations

used, applied, classified, widely

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

Gör

-1.04

меется

-1.03

vanie

-0.89

 ۱۳۸

-0.87

緋

-0.84

 لكل

-0.82

 máme

-0.81

cences

-0.81

姗

-0.81

 kteří

-0.80

POSITIVE LOGITS

 used

3.52

 widely

3.45

 широко

2.66

广泛

2.53

used

2.44

 Widely

2.31

wide

2.30

Used

2.22

 Used

2.14

 χρησιμοποι

2.06

Activations Density 0.362%