INDEX

Explanations

notice of intention

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

oint

-0.10

lich

-0.09

 rejo

-0.09

ooter

-0.09

 annunci

-0.09

lob

-0.09

 reported

-0.08

aki

-0.08

ched

-0.08

POSITIVE LOGITS

 intention

0.23

 intent

0.18

 existence

0.17

 intentions

0.17

 plans

0.16

intent

0.16

Intent

0.16

 availability

0.15

 Intent

0.14

 details

0.14

Activations Density 0.083%