INDEX

Explanations

code, decode, encoded, or coded

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

Negative Logits

Code

-0.12

_encoding

-0.12

Encoded

-0.11

Encoding

-0.11

soever

-0.11

 coding

-0.11

ÙĩÙħ

-0.11

 coded

-0.10

 cÃ³digo

-0.10

_code

-0.10

POSITIVE LOGITS

pend

0.20

URIComponent

0.16

.jquery

0.15

velop

0.15

velopment

0.14

ÐµÐºÑģ

0.13

../../../

0.12

breaker

0.12

gen

0.12

forces

0.11

Activations Density 0.057%

No Known Activations