INDEX

Explanations

prevalence proportioning commonality

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

 femei

-0.93

 oameni

-0.85

or

-0.84

 devemos

-0.83

 agresión

-0.82

 fallecimiento

-0.82

ンの

-0.82

 attraverso

-0.81

 alcuni

-0.79

 através

-0.79

POSITIVE LOGITS

(~

1.93

$(

1.89

1.80

($

1.73

(<

1.62

(>

1.54

(£

1.30

($\

1.24

 (€

1.22

$(

1.19

Activations Density 0.309%