INDEX

Explanations

names or titles followed by comma

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

ṝ

-1.64

 they

-1.60

 chré

-1.59

↵

-1.55

 выпе

-1.53

 τὴν

-1.51

ଶ

-1.49

 desejo

-1.49

囝

-1.48

 silêncio

-1.47

POSITIVE LOGITS

ּוֹ

2.67

ֶּ

2.16

וּ

2.08

ִּ

1.88

ֵּ

1.83

ַּ

1.78

tersebut

1.77

וּ

1.76

💽

1.70

 bandoulière

1.66

Activations Density 0.001%