INDEX

Explanations

find

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 find

-1.39

find

-0.90

 finden

-0.85

 finds

-0.79

 trouve

-0.79

 encontrar

-0.75

 trouver

-0.75

 found

-0.69

 Find

-0.68

 trouvent

-0.68

POSITIVE LOGITS

ers

0.80

afficheront

0.61

ings

0.59

 purpure

0.59

 crystallization

0.58

ably

0.54

ingly

0.54

 sphinct

0.54

 glabrous

0.54

utnik

0.50

Activations Density 0.009%