INDEX

Explanations

attribute values with leading slash

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

ꦼ

-2.39

其余

-2.22

 queridos

-2.19

 preocu

-2.17

 После

-2.16

 cómoda

-2.14

ссор

-2.09

ation

-2.08

 όταν

-2.08

 desempeño

-2.06

POSITIVE LOGITS

3.78

2.98

2.88

2.86

2.52

was

2.42

—”

2.34

2.30

2.22

 parco

2.17

Activations Density 0.002%