INDEX

Explanations

feeling sad or negative

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ỳnh

-2.47

?”

-2.41

过程中

-2.34



-2.28

鍇

-2.25

※※

-2.22

</h3>

-2.20

сро

-2.17

зывают

-2.16

 AWESOME

-2.14

POSITIVE LOGITS

</b>

2.77



2.70

⏑

2.45

 modificación

2.42

that

2.41

who

2.36

 ältere

2.31

-.

2.30

↵

2.23

Activations Density 0.001%