INDEX

Explanations

female names following phone numbers

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Nicholas

1.91

Nicholas

1.86

 Matthew

1.82

 Benjamin

1.81

 Joshua

1.78

Joshua

1.75

Benjamin

1.74

 Zachary

1.74

Matthew

1.73

 Andrew

1.73

POSITIVE LOGITS

 Barb

1.06

Barb

1.05

Sue

0.98

Judy

0.98

 Carol

0.97

 Judy

0.97

 patty

0.94

 Shirley

0.93

Peg

0.92

Bev

0.90

Activations Density 0.331%