INDEX

Explanations

character encoding via ord or code

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

é»İ

-0.11

 alphanumeric

-0.10

reck

-0.09

ind

-0.09

lak

-0.09

 suffix

-0.09

.readString

-0.08

Cab

-0.08

crest

-0.08

Tic

-0.08

POSITIVE LOGITS

Asc

0.16

.fromCharCode

0.16

ord

0.16

 character

0.15

ord

0.15

 codes

0.15

(ord

0.15

asc

0.15

 char

0.14

 code

0.14

Activations Density 0.069%