INDEX

Explanations

Code/Foreign Language/Scientific

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 from

-1.59

from

-1.48

From

-1.21

 FROM

-1.10

จาก

-1.09

 From

-1.07

 från

-1.02

 desde

-0.99

FROM

-0.99

 kutoka

-0.96

POSITIVE LOGITS

0.69

the

0.57

eryn

0.56

wirt

0.56

phorbia

0.55

 being

0.55

asthan

0.55

expandindo

0.53

 honor

0.52

 onBind

0.51

Activations Density 0.134%