INDEX

Explanations

automatically/directly/immediately followed by verb

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

кі

1.45

кая

1.27

с

1.22

ن

1.22

йти

1.20

 témoins

1.13

кому

1.13

م

1.13

ваме

1.12

ى

1.11

POSITIVE LOGITS

en

1.14

ल

1.03

ut

1.02

${

1.02

ls

1.00

 जानकर

0.96

 פּ

0.95

 dotycz

0.95

тбол

0.91

 appointing

0.90

Activations Density 0.147%