INDEX

Explanations

fun followed by descriptive noun

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

’

1.25

ร

1.23

ру

1.20

 genere

1.19

/>

1.18

ের

1.16

εργ

1.15

its

1.12

old

1.11

ों

1.11

POSITIVE LOGITS

رير

1.45

1.38

م

1.34

นี่

1.33

icularly

1.29

 resistors

1.29

larda

1.28

 nicknames

1.27

ский

1.25

erweise

1.25

Activations Density 0.005%