INDEX

Explanations

words starting with Sus

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

 algunos

-2.75

媄

-2.67

 nicht

-2.66

谖

-2.61

鸶

-2.55

 algunas

-2.53

퐿

-2.52

 findet

-2.45

seu

-2.44

 ciertos

-2.42

POSITIVE LOGITS

3.48

that

2.33

ti

2.30

ثيق

2.20

</i>

2.14

硨

2.13

isation

2.13

鮃

2.11

žený

2.08

 gatti

2.05

Activations Density 0.008%