INDEX

Explanations

source code

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

celona

-0.48

 Roskov

-0.40

 límites

-0.40

 çıkar

-0.36

 TextInputType

-0.35

 مرئيه

-0.35

 dessous

-0.35

 asal

-0.34

 tàn

-0.34

واعد

-0.34

POSITIVE LOGITS

0.79

 CURIAM

0.78

[](

0.68

 Patience

0.67

 Shaksp

0.65

 whoſe

0.65

şak

0.64

$_"

0.64

 ſmall

0.63

 ſeveral

0.63

Activations Density 0.018%