INDEX

Explanations

network includes and headers

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

Tham

-0.78

hoodie

-0.77

pen

-0.76

 helyez

-0.75

MCU

-0.75

Koordinaten

-0.74

 Receipts

-0.73

աշ

-0.72

 deaktivi

-0.71

ținut

-0.70

POSITIVE LOGITS

 geta

1.28

IPv

0.97

geta

0.94

 Inet

0.88

IPv

0.85

 Kosher

0.79

 hints

0.79

stris

0.79

 rodziny

0.79

 resol

0.77

Activations Density 0.016%