INDEX

Explanations

in followed by description

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

nargs

-1.62

if

-1.53

🤠

-1.50

 otros

-1.48

 outros

-1.45

 ľah

-1.44

ขอ

-1.43

 моя

-1.41

geries

-1.41

\\

-1.41

POSITIVE LOGITS

นาด

2.03

灕

1.66

同样的

1.65

たちも

1.59

畯

1.57

 indipendente

1.56

 kanskje

1.52

 übri

1.52

了一

1.51

htbp

1.51

Activations Density 0.032%