INDEX

Explanations

sameness and similarity

same / identical

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

MainActivityTest

0.44

٩

0.42

 véritable

0.40

 বিস্ফ

0.39

यत

0.38

 ಪ್ರತ

0.38

arakat

0.38

ಥವಾ

0.38

্্

0.38

ಾವ್

0.37

POSITIVE LOGITS

共通

1.72

 одина

1.55

相同的

1.51

相同

1.46

 identical

1.41

 동일

1.39

 same

1.31

 common

1.29

同一个

1.28

 hetzelfde

1.27

Activations Density 0.146%