INDEX

Explanations

as of today, date

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<unused1600>

2.27

<unused1515>

2.22

 curviliné

2.20

<unused1570>

2.19

<unused1518>

2.19

<unused1419>

2.18

<unused1506>

2.17

<unused1467>

2.17

<unused1332>

2.17

<unused1561>

2.16

POSITIVE LOGITS

3.98

1.48

app

1.46

1.38

1.35

1.31

1.28

res

1.25

MAT

1.25

1.24

Activations Density 0.329%