INDEX

Explanations

TV brands and models

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

 broadcasts

-0.14

 Broadcasting

-0.14

 broadcasting

-0.13

 broadcasters

-0.12

broadcast

-0.11

 Broadcast

-0.11

 Sensors

-0.10

_BINARY

-0.10

ensors

-0.10

 sensors

-0.10

POSITIVE LOGITS

 channel

0.22

TV

0.21

 channels

0.21

 tuner

0.19

 reception

0.18

TV

0.17

 satellite

0.17

 Channel

0.17

 Dish

0.16

 television

0.16

Activations Density 0.064%