INDEX

Explanations

Australian directors and entities

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

 duly

-0.09

 Gund

-0.09

 viol

-0.09

BB

-0.09

Pending

-0.09

pora

-0.09

âĶĤ

-0.09

itary

-0.09

WM

-0.09

SEC

-0.09

POSITIVE LOGITS

 directors

0.18

lod

0.16

 director

0.15

 Directors

0.14

Lod

0.13

 ASIC

0.13

director

0.12

 lodged

0.12

 prescribed

0.12

 Director

0.12

Activations Density 0.034%