INDEX

Explanations

cases

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 prêtres

-0.65

 âmes

-0.58

 religieuses

-0.58

 dirigentes

-0.56

 campeones

-0.56

 للاسماء

-0.54

 hombros

-0.54

 calcetines

-0.54

 morgon

-0.54

 larmes

-0.53

POSITIVE LOGITS

 swans

0.77

 oysters

0.73

 corals

0.72

 Spart

0.71

 flocks

0.71

 pigeons

0.68

 wasp

0.68

 lobsters

0.67

 seaweed

0.67

 bees

0.66

Activations Density 0.014%