INDEX

Explanations

variable declarations

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

1.61

tions

1.53

pak

1.35

park

1.30

trees

1.30

ulator

1.28

tails

1.26

ö

1.26

att

1.24

holes

1.24

POSITIVE LOGITS

مند

1.38

 Joanne

1.24

 Rosemary

1.22

 watermelon

1.21

 পাবার

1.19

 infecting

1.18

Бо

1.16

 diminishes

1.16

<bos>

1.15

೯

1.14

Activations Density 0.001%