INDEX

Explanations

build quality

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

 cond

-0.11

 settings

-0.10

vore

-0.10

 capacit

-0.10

 coils

-0.10

ippy

-0.09

 peanut

-0.09

ÅĻet

-0.09

 coil

-0.09

 Hutch

-0.09

POSITIVE LOGITS

 copper

0.19

 Copper

0.16

 contact

0.15

 contacts

0.14

 Redistribution

0.13

Cu

0.12

contact

0.12

 diss

0.12

bus

0.12

 Conduct

0.11

Activations Density 0.026%