INDEX

Explanations

character introduction after name

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

ekim

-0.09

aldo

-0.09

 Merlin

-0.09

ucher

-0.08

Occurred

-0.08

ayne

-0.08

aldi

-0.08

ipes

-0.08

ckill

-0.08

 trio

-0.08

POSITIVE LOGITS

 protagonist

0.11

 Bapt

0.10

 Beat

0.09

 intro

0.09

 main

0.09

 college

0.09

 Madison

0.09

verity

0.09

 Widgets

0.09

Ëĺ

0.09

Activations Density 0.344%