INDEX

Explanations

higher-order functions, decorators

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

 recess

-0.10

vos

-0.10

 Silk

-0.09

pis

-0.09

pha

-0.08

 getters

-0.08

CSL

-0.08

geom

-0.08

 Ricky

-0.08

 enum

-0.08

POSITIVE LOGITS

 closure

0.17

cur

0.17

 Closure

0.16

WRAPPER

0.16

 curry

0.16

 closures

0.15

Closure

0.15

closure

0.14

æŁ

0.14

½æķ°

0.13

Activations Density 0.077%