INDEX

Explanations

search and related operations

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

_search

-0.13

ocre

-0.12

SearchParams

-0.12

-0.10

 searchable

-0.10

-0.09

_SEARCH

-0.09

ÙĬÙĥÙĬ

-0.09

Search

-0.09

Įĵ

-0.09

POSITIVE LOGITS

es

0.20

able

0.18

ers

0.18

lights

0.17

light

0.17

er

0.17

 engine

0.16

ingly

0.15

 warrant

0.14

 engines

0.14

Activations Density 0.038%