INDEX

Explanations

seems like or sounds like

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

 tratamento

-1.00

킁

-0.99

変な

-0.97

 anuncia

-0.97

 nabízí

-0.96

の使い方

-0.96

containing

-0.95

 sorprende

-0.93

 aniversário

-0.92

POSITIVE LOGITS

 like

4.97

Like

2.33

like

2.19

 Like

1.83

 seperti

1.76

 như

1.74

像

1.67

LIKE

1.60

 LIKE

1.59

 مانند

1.51

Activations Density 0.029%