INDEX

Explanations

reduce heat or potential length

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

in

1.74

ar

1.33

 собой

1.31

is

1.25

ro

1.24

))

1.23

 dugo

1.22

на

1.21

yn

1.21

 capelli

1.20

POSITIVE LOGITS

 tratt

1.31

 chancellor

1.26

 recombin

1.22

 guardianship

1.18

Miami

1.16

Vitamin

1.13

 Chancellor

1.11

 totalitarian

1.10

⚫

1.10

ScheduledAction

1.09

Activations Density 0.000%