INDEX

Explanations

forbidden actions

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

 Couldn

-1.08

 bättre

-0.94

慎重

-0.94

Зміст

-0.94

稍微

-0.94

 maybe

-0.94

ayangkan

-0.93

 ਹੋ

-0.92

 Wouldn

-0.91

 properly

-0.91

POSITIVE LOGITS

use

1.57

 exceed

1.36

 rely

1.34

 attempt

1.26

 reuse

1.24

 EVER

1.23

Attempt

1.11

 leave

1.08

attempt

1.06

 attempts

1.04

Activations Density 0.039%