INDEX

Explanations

references to smoking

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

ंदीखरीदारी

-0.84

WebVitals

-0.79

 CreateTagHelper

-0.74

 bezeichneter

-0.73

ioutil

-0.68

miral

-0.68

 Costello

-0.66

XmlAccessType

-0.65

 Roskov

-0.63

ähig

-0.63

POSITIVE LOGITS

 smoking

2.97

 Smoking

2.61

 smokers

2.55

Smoking

2.53

smoking

2.52

 smoker

2.27

 smoke

2.14

 smoked

2.05

smoke

1.90

 smokes

1.88

Activations Density 0.014%