INDEX

Explanations

verb conjugation endings

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

zeigen

-0.10

 arrog

-0.10

 comple

-0.10

cheid

-0.09

ichern

-0.09

uze

-0.09

 underst

-0.09

_tpl

-0.09

 Lucia

-0.09

Wyn

-0.09

POSITIVE LOGITS

isiert

0.13

 worden

0.11

ellt

0.11

utzt

0.10

osen

0.10

ppt

0.10

 Knock

0.10

ilt

0.10

oken

0.09

ckt

0.09

Activations Density 0.045%