INDEX

Explanations

states/actions applied

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

 Give

1.00

 Yeah

0.98

 About

0.94

 Something

0.91

헛

0.86

 things

0.83

 Some

0.81

 tolle

0.80

..

0.80

New

0.80

POSITIVE LOGITS

 undergoes

1.50

ត្រូវបាន

1.48

 subjected

1.37

 treated

1.28

 được

1.25

 routinely

1.20

 periodically

1.18

 assigned

1.17

 undergone

1.16

 inserted

1.16

Activations Density 0.680%