INDEX

Explanations

combining and combinations

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

ovsky

-0.10

lj

-0.10

 Comic

-0.09

abler

-0.09

aurus

-0.09

 army

-0.09

rh

-0.09

 bÃ¡t

-0.09

arith

-0.09

 grav

-0.09

POSITIVE LOGITS

ination

0.19

obox

0.17

ining

0.17

inations

0.16

ines

0.14

 comb

0.13

tures

0.13

inator

0.12

(comb

0.12

atorial

0.12

Activations Density 0.021%