INDEX

Explanations

fancy followed by noun

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

 Pathways

-0.87

 rois

-0.86

ert

-0.85

 使っ

-0.85

 auffi

-0.84

pppp

-0.82

 テープ

-0.82

passengers

-0.81

 melody

-0.81

 Discrete

-0.81

POSITIVE LOGITS

 fancy

2.11

fancy

1.83

 Fancy

1.66

Fancy

1.59

pants

1.27

work

1.15

 fancies

1.15

 pants

1.05

 fanciful

1.04

ỡ

1.02

Activations Density 0.011%