INDEX

Explanations

encryption security

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

decoded

-0.11

 Decrypt

-0.10

APON

-0.09

Slim

-0.09

Decrypt

-0.09

 decrypted

-0.09

alem

-0.09

Decode

-0.09

 PureComponent

-0.08

æŁĦ

-0.08

POSITIVE LOGITS

enc

0.25

0.20

Enc

0.18

 strong

0.17

 strongest

0.17

 Transport

0.17

 encryption

0.16

 security

0.16

Enc

0.16

Activations Density 0.090%