INDEX

Explanations

describing actions or states with follow-up descriptions

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

 trebalo

1.34

缃

1.31

υ

1.24

 потом

1.23

м

1.22

zim

1.21

zur

1.16

 방식으로

1.14

ుడు

1.13

ный

1.12

POSITIVE LOGITS

 faithfully

1.33

sortie

1.32

 Arjuna

1.26

 Buddhism

1.25

pts

1.24

 размеры

1.23

он

1.22

 turmoil

1.21

 duplicates

1.21

 artériel

1.17

Activations Density 0.000%