INDEX

Explanations

not locked or sampled

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

TransparentColor

-0.11

 Lime

-0.10

 shade

-0.09

.::

-0.09

shade

-0.09

 shades

-0.09

fen

-0.09

Nex

-0.09

EDGE

-0.08

 Shannon

-0.08

POSITIVE LOGITS

 property

0.18

 inspector

0.16

 Property

0.16

 Inspector

0.15

 properties

0.14

Property

0.14

Inspector

0.14

property

0.14

 propiedad

0.13

-property

0.13

Activations Density 0.043%