INDEX

Explanations

these facts, following conditions, associated with

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

 Nong

-0.81

cron

-0.78

newtheorem

-0.76

chase

-0.76

chait

-0.75

hoek

-0.74

 Cornwall

-0.73

 Brass

-0.71

 Cron

-0.71

ویت

-0.71

POSITIVE LOGITS

 things

3.28

 thing

2.86

 điều

2.78

 बात

2.33

 matter

2.30

Things

2.28

 Things

2.27

 matters

2.27

ること

2.25

こと

2.09

Activations Density 0.007%