INDEX

Explanations

abstract class method definitions

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

 stew

-0.10

keh

-0.10

afort

-0.09

Accessor

-0.09

Constructor

-0.09

Gil

-0.09

 Tunnel

-0.09

 Felix

-0.09

 Paginator

-0.09

inity

-0.08

POSITIVE LOGITS

 concrete

0.29

 Concrete

0.26

Concrete

0.23

 abstract

0.22

 factory

0.19

 Abstract

0.18

 Factory

0.17

 Strategy

0.16

abstract

0.16

_abstract

0.16

Activations Density 0.050%