INDEX

Explanations

just/get/bit/got/lots/tired

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

 firme

1.29

 році

1.28

적으로

1.27

 efect

1.21

 ап

1.20

是我

1.19

 direc

1.19

}}"

1.17

போன்ற

1.16

 claire

1.15

POSITIVE LOGITS

al

1.50

ス

1.37

På

1.30

ด

1.24

1.23

1.21

UCK

1.19

 bruising

1.17

IL

1.15

म

1.13

Activations Density 2.653%