INDEX

Explanations

words ending in ine or inal

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

ening

-0.13

    \n    \n    \n    \n

-0.11

time

-0.11

ened

-0.11

wards

-0.11

line

-0.11

EFA

-0.11

âĸĪâĸĪ

-0.10

ifications

-0.10

rome

-0.10

POSITIVE LOGITS

ning

0.18

ners

0.15

ering

0.14

omial

0.13

ergy

0.13

ocular

0.13

NING

0.13

arity

0.12

fold

0.12

stagram

0.12

Activations Density 0.214%