INDEX

Explanations

2FA codes from assistant

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

 encrypt

-0.10

 Encryption

-0.09

 Evan

-0.09

Encryption

-0.09

ful

-0.09

Unauthorized

-0.09

 encryption

-0.09

XD

-0.09

ï¾Ł

-0.09

 decrypt

-0.09

POSITIVE LOGITS

 code

0.21

 codes

0.19

Code

0.17

_tot

0.17

code

0.17

 Code

0.16

Tot

0.16

.setCode

0.16

QR

0.16

TOT

0.16

Activations Density 0.032%