INDEX

Explanations

applied to automate

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

 formula

-0.10

 substr

-0.10

RAW

-0.10

 determin

-0.10

 optimal

-0.09

 linear

-0.09

formula

-0.09

 electronic

-0.09

 lawful

-0.09

 machinery

-0.08

POSITIVE LOGITS

 physics

0.13

 Physics

0.11

_lhs

0.11

physics

0.10

 Param

0.10

 Gover

0.10

TRL

0.10

 Reynolds

0.10

 Perkins

0.09

 numer

0.09

Activations Density 0.156%