INDEX

Explanations

ca

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

CWE

-0.71

<bos>

-0.64

Personendaten

-0.60

✎

-0.59

InjectAttribute

-0.59

EndGlobalSection

-0.57

simpleType

-0.56

 this

-0.56

ReusableCell

-0.55

Արտաքին

-0.55

POSITIVE LOGITS

 Sociale

0.56

 Democrá

0.54

 ſtand

0.50

 paſſ

0.49

Eſ

0.48

 progrès

0.47

 robuste

0.47

 cív

0.47

 neceſſ

0.46

 onely

0.46

Activations Density 0.010%