INDEX

Explanations

also followed by verbs

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

-1.93

 như

-1.63

 idyllic

-1.54

-1.53

看了看

-1.48

を使用した

-1.46

 обеспечить

-1.44

 именно

-1.41

并没有

-1.40

真剣

-1.40

POSITIVE LOGITS

or

2.06

踐

1.64

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.50

越來越

1.49

！”

1.45

頹

1.44

in

1.43



1.40

總是

1.38

and

1.36

Activations Density 0.059%