INDEX

Explanations

acts of violence, extreme situations

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

各地

-1.12

 many

-1.10

͚

-1.02

많

-1.01

 vždy

-1.00

 خاصی

-1.00

 always

-1.00

емый

-0.99

hichever

-0.99

 các

-0.98

POSITIVE LOGITS

しかも

1.75

 semejante

1.66

 dessutom

1.59

 столь

1.54

いきなり

1.46

 such

1.36

わざわざ

1.30

这么

1.23

これだけ

1.23

 addirittura

1.23

Activations Density 0.151%