INDEX

Explanations

hexadecimal identifiers

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

 ensures

-1.79

私には

-1.73

 absurdo

-1.70

 involves

-1.69

 године

-1.63

この時期

-1.63

以上です

-1.60

-1.57

 requires

-1.56

 retains

-1.56

POSITIVE LOGITS

2.30

geleitet

1.77

 …)

1.66

selbe

1.63

骉

1.63

轳

1.57

 verheir

1.57



1.54

ᯅ

1.49

==",

1.45

Activations Density 0.008%