INDEX

Explanations

numbers followed by specific words

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

ة

1.63

1.46

য়নের

1.36

1.30

𝘺

1.28

য়

1.22

첫

1.22

я

1.19

ரிக

1.18

ed

1.17

POSITIVE LOGITS

 inadequ

1.64

 lacking

1.45

 fraudulently

1.37

 stationery

1.32

 adjour

1.32

 wipes

1.30

 embroidery

1.27

 setData

1.27

 phag

1.26

 divides

1.24

Activations Density 0.000%