INDEX

Explanations

phrases that contrast something with something else

comparisons

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

IntoConstraints

-0.77

 CreateTagHelper

-0.74

 calendriers

-0.73

NOPQRST

-0.70

AddTagHelper

-0.66

 EconPapers

-0.66

tanleria

-0.62

 الحره

-0.62

uxxxx

-0.61

]=>

-0.60

POSITIVE LOGITS

 similar

0.54

similar

0.47

ly

0.45

 Green

0.43

 같은

0.43

 green

0.43

so

0.43

 hason

0.43

 comparable

0.41

oda

0.41

Activations Density 1.128%