INDEX

Explanations

historical and societal change

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

ern

1.24

 honti

1.24

speople

1.22

sion

1.20

ень

1.20

GO

1.16

اجة

1.13

钗

1.13

ارة

1.12

 pequenas

1.12

POSITIVE LOGITS

it

1.28

 परन्तु

1.27

등

1.23

يش

1.21

ться

1.20

 didn

1.18

つの

1.18

гүй

1.18

𝙢

1.16

 were

1.15

Activations Density 0.000%