INDEX

Explanations

interface methods access

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

以前的

-0.96

 dlouho

-0.95

原来的

-0.94

 المعيار

-0.93

 hiçbir

-0.92

 accél

-0.89

wouldn

-0.88

ultades

-0.88

kemeja

-0.88

 hés

-0.88

POSITIVE LOGITS

 each

1.71

its

1.56

各

1.30

the

1.12

其

1.11

数据的

1.10

その

1.08

how

1.07

每个

1.04

问题的

1.04

Activations Density 0.010%