INDEX

Explanations

personal topics and experiences

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

↵↵↵↵↵↵↵↵↵↵↵

-1.32

 they

-1.30

 étages

-1.30

jų

-1.30

 their

-1.25

🡪

-1.20

↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.20

 burch

-1.15

vė

-1.15

↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.15

POSITIVE LOGITS

my

2.88

 mojej

1.34

 почти

1.33

1.31

our

1.25

 meinem

1.25

 моих

1.22

tranh

1.18

 мои

1.18

 myself

1.18

Activations Density 0.141%