INDEX

Explanations

earlier this week/month/year

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

and

-3.06

二年

-2.16

 atractiva

-2.06

 mercancías

-1.92

 will

-1.91

咄

-1.88

咳

-1.86

 acoged

-1.83

 cómoda

-1.81

 originalmente

-1.74

POSITIVE LOGITS

2.28

1.99

あっという間に

1.93

嵓

1.86

個人的には

1.77

比较好

1.70

お昼

1.69

1.66

Activations Density 0.010%