INDEX

Explanations

sensory and intimate descriptions

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

UTERS

-0.09

tsy

-0.09

 heart

-0.09

 Whip

-0.09

CENTER

-0.08

 blister

-0.08

 repl

-0.08

ÏĦÏħ

-0.08

 sampling

-0.08

POSITIVE LOGITS

 room

0.20

 sound

0.15

 muscles

0.14

room

0.14

 Room

0.14

 sight

0.14

Room

0.13

 smell

0.13

 sensation

0.13

 force

0.12

Activations Density 0.020%