INDEX

Explanations

electrical power/devices

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÑĤÑĢÐ°

-0.28

inder

-0.27

 motivating

-0.25

ç¥ķ

-0.24

 misses

-0.24

åģľå·¥

-0.24

entar

-0.24

æ³¯

-0.24

Forest

-0.24

åĬ¨çī©åĽŃ

-0.23

POSITIVE LOGITS

 household

0.34

 Household

0.33

Ð±Ð»

0.32

å®¶çĶµ

0.31

æıĴ

0.30

 devices

0.29

è®¾å¤ĩ

0.29

 device

0.28

å®¶çĶ¨

0.28

-device

0.27

Activations Density 0.886%