INDEX

Explanations

feminine form and grammatical cases

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

 verb

-0.15

 Verb

-0.12

 verbs

-0.11

 Wich

-0.10

Verb

-0.10

Ì£

-0.09

Mer

-0.09

verb

-0.09

iosa

-0.08

ver

-0.08

POSITIVE LOGITS

 neut

0.20

 accus

0.15

 decl

0.13

 nomin

0.13

sg

0.12

Decl

0.12

.sg

0.12

 animate

0.12

 intensive

0.11

decl

0.11

Activations Density 0.053%