INDEX

Explanations

the word "drain."

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

PhysRev

-1.03

AndEndTag

-0.97

 MainAxisSize

-0.88

Према

-0.86

onAttach

-0.84

onViewCreated

-0.84

ViewImports

-0.82

PhysRevD

-0.81

 Presby

-0.80

DoubleQuotes

-0.79

POSITIVE LOGITS

drained

1.35

 drain

1.33

 DRAIN

1.29

 Drain

1.28

 drains

1.23

 drained

1.22

 draining

1.20

Drain

1.17

drain

1.13

 drainage

1.10

Activations Density 0.004%