INDEX

Explanations

a/an followed by word

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

鱻

-2.17

参

-1.69

 短发

-1.68

蟊

-1.60

-1.59

Yet

-1.58

 kompeti

-1.56



-1.55

鰱

-1.55

ﻦ

-1.55

POSITIVE LOGITS

或者

1.94

 also

1.84

 también

1.83

さんも

1.73

さんの

1.62

 également

1.60

 Каждый

1.57

などを

1.55

헉

1.54

 каждого

1.51

Activations Density 0.007%