INDEX

Explanations

words ending in -ly or -ity

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

INESS

-0.10

asio

-0.10

PickerController

-0.09

EMPLARY

-0.09

ÅŁt

-0.09

pread

-0.09

 gezocht

-0.09

cilik

-0.09

MLE

-0.09

ÏģÎ¹Ïĥ

-0.09

POSITIVE LOGITS

ly

1.36

LY

0.66

lys

0.34

lya

0.31

ity

0.28

ÑģÑı

0.28

ness

0.27

mente

0.27

ally

0.26

ities

0.24

Activations Density 0.138%