INDEX

Explanations

place names and groups

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

),

-2.53

濑

-2.36

韡

-2.34

 związane

-2.31

 techniczne

-2.20

 erforder

-2.17

medriver

-2.16

鄖

-2.11

आर

-2.09

􀂃

-2.09

POSITIVE LOGITS

your

2.72

𖣘

2.59

</i>

2.52

栳

2.42

よろしくお願いします

2.36

ꨄ

2.34

</b>

2.33

蟶

2.27

 herr

2.25

 ваша

2.25

Activations Density 0.003%