INDEX

Explanations

four motors and sensors

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

ORIZ

-0.11

 flick

-0.10

CGI

-0.10

OMET

-0.10

 Arap

-0.09

 bench

-0.09

 fighters

-0.09

abox

-0.09

inv

-0.09

 Sachs

-0.09

POSITIVE LOGITS

 bump

0.16

 obstacle

0.15

 wheels

0.14

 bumper

0.14

Rob

0.13

 obstacles

0.13

Whe

0.13

whe

0.13

 robot

0.12

éļľ

0.12

Activations Density 0.063%