INDEX

Explanations

describing roles or actions

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

ೌ

0.22

 parallelogram

0.21

?$

0.21

Facility

0.21

LGBT

0.20

 आहोत

0.19

 beve

0.19

 пять

0.19

 двох

0.19

 необхідно

0.19

POSITIVE LOGITS

’

0.29

ktions

0.24

0.23

/"

0.22

io

0.22

at

0.21

čnosti

0.21

iv

0.20

Activations Density 0.044%