INDEX

Explanations

study and learn

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

 fellow

-0.09

 Listener

-0.09

 adept

-0.09

ellow

-0.09

ãĢĢãĥ¾

-0.08

 hobby

-0.08

 asleep

-0.08

.Listener

-0.08

ighbor

-0.08

 Thread

-0.08

POSITIVE LOGITS

 familiar

0.35

Fam

0.31

 study

0.24

 learn

0.24

fam

0.23

amiliar

0.22

 Study

0.21

çĨŁ

0.21

study

0.20

åŃ¦ä¹ł

0.20

Activations Density 0.121%