INDEX

Explanations

numpy arrays are equal

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

bul

-0.10

 polar

-0.10

å¸Ń

-0.10

 forum

-0.09

 Palace

-0.09

 Dirt

-0.09

 Shaw

-0.09

FR

-0.09

osp

-0.09

 tact

-0.09

POSITIVE LOGITS

 array

0.17

.npy

0.15

array

0.14

arr

0.14

rray

0.13

 arrays

0.13

 shape

0.13

np

0.13

 dtype

0.13

(array

0.13

Activations Density 0.060%