INDEX

Explanations

Dod

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

issance

-0.25

secure

-0.24

 Palin

-0.24

alte

-0.24

éª¨

-0.24

 socialism

-0.23

.acquire

-0.23

acco

-0.23

çº¯

-0.23

é²Ī

-0.23

POSITIVE LOGITS

ero

0.30

èĢĮåİ»

0.29

pad

0.29

cles

0.28

wo

0.26

Pad

0.25

While

0.24

 readonly

0.24

Activations Density 0.041%