INDEX

Explanations

short answer

short content descriptions

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ה

0.73

ม

0.70

та

0.66

को

0.63

の詳細

0.60

のス

0.59

자

0.58

</h2>

0.56

ita

0.56

ंग

0.55

POSITIVE LOGITS

 short

1.53

short

1.50

 corto

1.41

短

1.41

 shortened

1.41

 корот

1.40

짧

1.38

 curto

1.36

 shorten

1.35

 کوتاه

1.33

Activations Density 0.046%