INDEX

Explanations

person writes something

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

’

-2.09

𓆟

-1.79

 каким

-1.73

적으로

-1.63

}{

-1.62

麒

-1.59

杞

-1.57

ă

-1.56

 aren

-1.55

 abiertos

-1.55

POSITIVE LOGITS



1.98

⦊

1.88

もう一度

1.82

 verbess

1.80

 recientemente

1.75

涐

1.72

 píše

1.71

 recentemente

1.70



1.67

 electrónicos

1.64

Activations Density 0.020%