INDEX

Explanations

got followed by possession or state

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

탉

-2.02

𖤣

-1.91

韜

-1.88

猡

-1.87



-1.79

 caneca

-1.77

</h5>

-1.76

Cuando

-1.75

 мы

-1.73

When

-1.73

POSITIVE LOGITS

</strong>

2.56

và

2.17

และ

2.13

依然

2.00

et

1.98

ностей

1.95

“,

1.89

ኧ

1.89

ation

1.85

 Сам

1.83

Activations Density 0.007%