INDEX

Explanations

not so \[adjective/adverb]

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

-1.83

蒸し

-1.70

再び

-1.63

鹀

-1.63

hasilkan

-1.52

ありました

-1.52

 After

-1.51

⸨

-1.50

 would

-1.46

擁有

-1.45

POSITIVE LOGITS

for

1.86

 особенно

1.73

 刺繍

1.70

’

1.53

真正

1.53

ль

1.52

particularly

1.49

 also

1.48

 maria

1.48

those

1.48

Activations Density 0.005%