INDEX

Explanations

specific concepts like NER, authentication, or equality

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

 Granny

0.29

 Aboriginal

0.28

 Community

0.27

::

0.26

 aboriginal

0.26

 Gaelic

0.26

the

0.25

 Jersey

0.25

 Hawaiian

0.25

POSITIVE LOGITS

 odak

0.29

geteilt

0.25

 kontinuier

0.25

 impasse

0.25

 procédures

0.24

쾨

0.24

 velike

0.24

ില്‍

0.23

 privind

0.23

 střed

0.23

Activations Density 0.160%