INDEX

Explanations

selectivity

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

selective

-1.20

 selective

-1.08

Selective

-1.05

 Selective

-1.02

 selectivity

-0.85

exclusive

-0.83

 selectively

-0.79

 exclusivity

-0.73

Exclusive

-0.72

 exclusive

-0.66

POSITIVE LOGITS

AndEndTag

0.70

KURZBESCHREIBUNG

0.67

StructEnd

0.67

########.

0.67

 lava

0.65

 Theſe

0.65

(++

0.63

EDEFAULT

0.62

CWE

0.61

Билгалдахарш

0.61

Activations Density 0.014%