INDEX

Explanations

`false` `attach` `boolean`

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

 what

-0.90

 joão

-0.82

borderSide

-0.76

setResult

-0.75

ToUpdate

-0.73

how

-0.73

 silang

-0.73

 iyon

-0.71

了一会儿

-0.71

 Primeiro

-0.70

POSITIVE LOGITS

 false

1.79

false

1.66

 attach

1.21

 False

1.20

 Attach

1.15

 attachment

1.13

 attaching

1.12

 boolean

1.09

attach

1.06

 FALSE

1.05

Activations Density 0.004%