INDEX

Explanations

mathematical and code execution context

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

 heft

1.57

 morphed

1.41

 horrend

1.40

&/

1.37

 bolstering

1.34

 underwhelming

1.29

 birt

1.29

 bevy

1.29

Mapped

1.26

 dabb

1.21

POSITIVE LOGITS

";

1.30

Ს

1.29

prü

1.26

 informat

1.24

Მ

1.23

ordinary

1.22

 ordinary

1.22

Გ

1.22

ü

1.22

Всем

1.20

Activations Density 0.269%