INDEX

Explanations

it was / we didn't

past tense verbs like was/were

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 हैं

0.94

ходят

0.92

합니다

0.89

 можуть

0.82

 mohou

0.82

があります

0.82

 obecnie

0.81

 ہے

0.80

 आहे

0.79

됩니다

0.78

POSITIVE LOGITS

 était

1.83

 ήταν

1.79

 była

1.79

 buvo

1.75

 étaient

1.71

 vardı

1.64

이었다

1.63

 была

1.60

was

1.57

 είχε

1.57

Activations Density 1.197%