INDEX

Explanations

rinsing and residues

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

 washing

-1.21

 cleaning

-1.17

 washes

-1.15

 wash

-1.13

Cleaning

-1.13

 WASH

-1.07

 washed

-1.06

Wash

-1.02

 Wash

-1.02

Washing

-1.00

POSITIVE LOGITS

 rinse

2.06

 rinsing

1.65

 rinsed

1.59

 Rinse

1.58

Rinse

1.41

 residue

1.15

 final

1.10

すす

1.02

 rins

0.95

 residues

0.92

Activations Density 0.019%