INDEX

Explanations

War

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

liter

-0.30

ÈĻ

-0.27

æľŁåĨħ

-0.27

bilder

-0.27

éĹ´éļĻ

-0.27

Sensitive

-0.26

ãĥĪãĥ«

-0.25

.activ

-0.25

åı£ä¸Ń

-0.25

fÃ¶rder

-0.24

POSITIVE LOGITS

 reap

0.28

 impl

0.26

èĩªä¸»åĵģçīĮ

0.26

 gode

0.24

æĹĹå¸ľ

0.24

åİ»å¹´

0.24

Led

0.24

 Iris

0.23

ForRow

0.23

 experienced

0.23

Activations Density 0.001%