INDEX

Explanations

variable names abbreviations

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

-1.59

わずか

-1.57

 first

-1.47

 before

-1.46

 بشه

-1.42

Surprisingly

-1.41

-1.36

 äußerst

-1.32

 Surprisingly

-1.31

 keineswegs

-1.31

POSITIVE LOGITS

 этих

1.59

 них

1.50

 diſ

1.48

 carcasa

1.45

 andere

1.39



1.34

<tr>

1.34

).}

1.30

回到了

1.30

’).

1.27

Activations Density 0.018%