INDEX

Explanations

reference material titles

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

 aceea

-1.21

↵

-1.20

 same

-1.17

馬上

-1.17

 conformidad

-1.15

之後

-1.14

 stessa

-1.14

 ähn

-1.14

 okrąg

-1.12

tbx

-1.11

POSITIVE LOGITS

ременно

1.43

for

1.38

CURLOPT

1.24

Kesimpulan

1.23

 Ван

1.23

 сан

1.22

田村

1.21

ХОД

1.20

вам

1.20

 alebo

1.20

Activations Density 0.012%