INDEX

Explanations

list item markers

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

在那里

0.83

 there

0.82

 расстоя

0.80

and

0.79

你了

0.77

 then

0.76

 thereof

0.74

there

0.73

 അവിടെ

0.72

走向

0.72

POSITIVE LOGITS

 thrilled

1.32

 dismay

1.31

 enthusi

1.30

 surprise

1.27

 delighted

1.24

 eagerly

1.24

惊讶

1.24

surprise

1.23

 surprised

1.22

 excitedly

1.22

Activations Density 0.350%