INDEX

Explanations

scoring runs

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

 novedad

-0.93

wäsche

-0.90

 conducir

-0.85

Learn

-0.81

plätze

-0.81

WhereInput

-0.77

 reproducir

-0.76

一天

-0.75

 broadcasting

-0.74

daction

-0.73

POSITIVE LOGITS

run

1.58

 runs

1.58

 Runs

1.10

 unanswered

1.07

Run

1.03

run

1.03

 spurt

1.03

runs

1.02

Runs

1.02

Run

0.95

Activations Density 0.005%