INDEX

Explanations

RS and RS variants

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

 readily

-0.78

我们需要

-0.76

 ngừng

-0.75

टर

-0.75

 something

-0.73

 thirds

-0.71

 ماش

-0.70

 literally

-0.70

 Literally

-0.69

Literally

-0.68

POSITIVE LOGITS

RS

1.03

rs

0.83

酶

0.82

 perspectiva

0.82

マイズ

0.81

 лист

0.80

 Fiscalía

0.79

niken

0.79

 スカート

0.77

uronic

0.77

Activations Density 0.030%