INDEX

Explanations

words ending in "ate"

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

℉

-0.88

losse

-0.86

''')

-0.85

 تضيفلها

-0.82

dubbo

-0.80

Previews

-0.80

fung

-0.78

 Divis

-0.77

gemm

-0.77

 Sequo

-0.76

POSITIVE LOGITS

uminate

0.90

ate

0.90

bate

0.88

ATE

0.88

uate

0.84

ated

0.84

nate

0.81

ates

0.81

 Bate

0.80

 Peralta

0.79

Activations Density 0.139%