INDEX

Explanations

slavery, slave, enslaved

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

匱

-0.81

 trout

-0.80

 копия

-0.75

 niez

-0.73

 Vater

-0.73

HideInInspector

-0.73

 nozzle

-0.73

 withdrawal

-0.71

layouts

-0.71

 Ladies

-0.70

POSITIVE LOGITS

 slavery

3.88

 slave

3.69

 slaves

3.33

 Slavery

3.02

slave

2.98

 Slave

2.80

 enslaved

2.75

slavery

2.70

Slave

2.61

 ensla

2.53

Activations Density 0.027%