INDEX

Explanations

"wheel" followed by a word

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

czegóły

-1.05

↵

-0.93

}^\

-0.89

 medži

-0.88

 weak

-0.86

-0.81

])){

-0.79

Même

-0.78

-0.77

POSITIVE LOGITS

barrow

1.73

 Kullan

1.05

 spokes

1.03

spin

1.00

 Wheel

0.98

ersburg

0.95

幸运

0.93

ksiä

0.91

CHAIR

0.91

BASE

0.91

Activations Density 0.013%