INDEX

Explanations

positive / positively / fairly / absolutely

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

</tfoot>

-1.79

voer

-1.75

 réfugi

-1.69

 "..\..\

-1.66

alties

-1.66

 fraî

-1.65

omorphisms

-1.64



-1.61

 katika

-1.57

ní

-1.56

POSITIVE LOGITS

↵

1.70

 ausreich

1.52

态度

1.51

If

1.48

”;

1.44

 want

1.42

;”

1.38

 aktiven

1.36

要

1.33

 southeast

1.30

Activations Density 0.012%