INDEX

Explanations

specific characteristics

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

ebly

-0.88

ществует

-0.87

uları

-0.85

 americanos

-0.84

ubat

-0.83

beke

-0.82

 Gentleman

-0.81

mayı

-0.79

 Popis

-0.79

$__

-0.79

POSITIVE LOGITS

 specific

4.78

specific

4.00

 unique

3.53

Specific

3.48

 Specific

3.19

 специфи

3.13

 spécifique

3.08

SPECIFIC

3.06

unique

2.98

เฉพาะ

2.88

Activations Density 0.211%