INDEX

Explanations

all, all, all, all, all

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

undry

-0.11

ANY

-0.10

Anything

-0.09

-0.08

(any

-0.08

 cualquier

-0.08

phin

-0.08

eworld

-0.08

ê²©

-0.08

ESIS

-0.08

POSITIVE LOGITS

all

0.47

æīĢæľī

0.39

 táº¥t

0.37

 Ð²ÑģÐµÑħ

0.34

 wszyst

0.32

 semua

0.31

 vÅ¡ech

0.30

 Ð²ÑģÐµ

0.29

ALL

0.29

 vÅ¡echny

0.28

Activations Density 0.173%