INDEX

Explanations

personal background details

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verity

-0.09

berger

-0.09

enga

-0.09

_Lean

-0.08

aho

-0.08

 ÐºÐ¸ÑģÐ»

-0.08

pcodes

-0.08

uros

-0.08

 brightest

-0.08

burger

-0.08

POSITIVE LOGITS

 background

0.22

bi

0.19

 personal

0.17

 information

0.17

bio

0.16

 details

0.16

background

0.16

 facts

0.16

Background

0.16

 Background

0.15

Activations Density 0.212%