INDEX

Explanations

normative and affective

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

<bos>

-2.44

onatos

-2.25

$^{

-1.98

穑

-1.97

 occupé

-1.97

鳎

-1.92

好似

-1.88

岿

-1.86

 tenté

-1.86

medriver

-1.86

POSITIVE LOGITS

2.34

↵↵

2.13

1.98

1.90

 seldom

1.70

ちゃんの

1.68

1.67

ちゃんは

1.60

 MUNDO

1.54

م

1.54

Activations Density 0.002%