INDEX

Explanations

police operations and investigations

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

 policeman

-0.10

 theft

-0.10

 detective

-0.10

ÐµÐ´Ð¶

-0.09

 Theft

-0.09

 Thief

-0.09

DIRECTORY

-0.09

 takeover

-0.09

cipher

-0.09

CLAIM

-0.09

POSITIVE LOGITS

 bust

0.28

 sting

0.23

 appreh

0.23

 Bust

0.20

 intelligence

0.20

 raids

0.18

 arrest

0.18

 raid

0.17

 Operation

0.17

 operation

0.16

Activations Density 0.046%