INDEX

Explanations

turkish greetings "ben"

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

Negative Logits

 MÃ¼ÅŁ

-0.17

 AÃ§Ä±k

-0.16

 Ä°z

-0.16

Ä±rak

-0.16

 KiÅŁ

-0.16

 Ä°nsan

-0.15

 Ä°li

-0.15

 DÃ¼ÅŁ

-0.15

 SÃ¶z

-0.15

 Onun

-0.15

POSITIVE LOGITS

ve

0.16

Bir

0.14

 Ð¿ÑĢÐ¾ÑĦÐµÑģÑģÐ¸Ð¾Ð½Ð°Ð»ÑĮ

0.13

ile

0.11

orum

0.11

Duy

0.11

bir

0.11

 ÐµÑģÑĤÐµ

0.11

Bir

0.10

 Alan

0.10

Activations Density 0.122%

No Known Activations