INDEX

Explanations

listing parallel items

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

 same

-1.59

 большим

-1.58

ACIONAL

-1.58

其它

-1.57

 fichas

-1.56

tenths

-1.56

 别墅

-1.55

 others

-1.55

ácio

-1.53

⟐

-1.52

POSITIVE LOGITS

of

1.97

了啊

1.91

op

1.85

赁

1.77

 '/')

1.73

1.71

然而

1.69

Þ

1.69

,/

1.67

1.66

Activations Density 0.006%