INDEX

Explanations

speech processing and assistant 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

chg

-0.09

 zend

-0.09

bum

-0.09

 Ð²Ð±

-0.08

à¸²à¸¨

-0.08

 Ø§ÙĦØªØ±

-0.08

ä¹ħ

-0.08

ylon

-0.08

 Spam

-0.08

éĺ

-0.08

POSITIVE LOGITS

 pitch

0.20

 speech

0.20

 pros

0.20

 speaker

0.19

 Speaker

0.18

 Pros

0.18

 utter

0.17

cep

0.16

 Speech

0.15

 Pitch

0.15

Activations Density 0.088%