INDEX

Explanations

scientific classifications and citations

citations in academic and scientific texts.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

£

-0.88

<b>

-0.81

 From

-0.76

 “…

-0.74

dhism

-0.73

 kurzer

-0.69

How

-0.68

 Solution

-0.68

<strong>

-0.67

↵↵↵

-0.67

POSITIVE LOGITS

<em>

1.29

textit

1.03

<i>

0.96

 Prejudice

0.94

 condicionado

0.91

悭

0.86



0.85

齶

0.81

 ADJUST

0.80

Activations Density 0.059%