INDEX

Explanations

words with positive or negative connotations, often related to effort or health

say "as"

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

 than

-0.68

 ніж

-0.56

Than

-0.55

 niż

-0.55

 decât

-0.50

 rispetto

-0.50

ciclopedia

-0.48

than

-0.48

 referenties

-0.48

 THAN

-0.47

POSITIVE LOGITS

as

1.98

 sebagai

1.13

 quanto

0.95

 как

0.91

as

0.91

sebagai

0.91

 jako

0.87

 Sebagai

0.87

作为

0.86

IntoConstraints

0.86

Activations Density 1.452%