INDEX

Explanations

code declarations and foreign words

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

ּוֹ

-2.22

in

-2.16

for

-2.00

ִּ

-1.88

 other

-1.84

ַּ

-1.80

 during

-1.75

过于

-1.73

ֶּ

-1.68

of

-1.67

POSITIVE LOGITS

 religieuses

1.93

 chré

1.77

 diriger

1.74

᾿

1.63

 メニュー

1.60

 τὰ

1.55

 ἐκ

1.52

 lámparas

1.51

 Jefus

1.51

 två

1.51

Activations Density 0.338%