INDEX

Explanations

explaining model details

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

რ

0.66

 поча

0.63

alit

0.62

'':

0.62

$.)

0.61

 ہوا۔

0.61

 স্বাক্ষর

0.61

wyk

0.60

 nije

0.60

 tiden

0.59

POSITIVE LOGITS

 doubtless

1.45

 onerous

1.45

 potentialities

1.29

 metropolis

1.29

 sizzling

1.27

 magnificence

1.26

 mannequin

1.24

 comparability

1.19

 scorching

1.15

 cowl

1.14

Activations Density 0.007%