INDEX

Explanations

words associated with sports categories and clubs, and potentially other classification categories

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 חיצוניים

-1.00

Personensuche

-0.89

허

-0.85

 دیکھیے

-0.80

 &___

-0.77

principalColumn

-0.77

 صوتيه

-0.77

 numberOfRows

-0.75

 AssemblyCulture

-0.74

twimg

-0.74

POSITIVE LOGITS

zieć

0.45

0.41

 samband

0.38

 discrepan

0.36

momile

0.35

 situés

0.34

جب

0.34

DESCRIPTION

0.33

versed

0.33

Activations Density 0.028%