INDEX

Explanations

companion and its context

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

ulação

0.40

ड

0.40

бы

0.39

каде

0.39

৬

0.39

itec

0.39

敵人

0.39

Avoid

0.38

adito

0.38

름

0.38

POSITIVE LOGITS

 companionship

1.33

 accompany

1.31

 companion

1.27

 accompanies

1.26

 accompaniment

1.19

companion

1.17

 acompañ

1.16

伴

1.16

 Companion

1.11

 acompanhar

1.10

Activations Density 0.006%