INDEX

Explanations

words and phrases relating to the past, eras, and time

specific terms or identifiers across different languages

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

Negative Logits

 time

-2.47

time

-2.03

Time

-1.84

 Time

-1.80

 TIME

-1.76

 times

-1.73

TIME

-1.67

 tijd

-1.43

times

-1.39

 tyme

-1.39

POSITIVE LOGITS

bkz

0.58

exitRule

0.46

 المعيارى

0.44

입

0.42

隔

0.41

AndEndTag

0.40

Clik

0.40

 Daly

0.39

фар

0.39

AccessType

0.39

Activations Density 2.645%