INDEX

Explanations

was part of

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

now

-2.45

 currently

-1.95

现在的

-1.41

现在

-1.40

now

-1.38

Currently

-1.38

 sekarang

-1.37

currently

-1.35

ícias

-1.27

今は

-1.27

POSITIVE LOGITS

was

1.97

 originally

1.85

 last

1.75

 وكان

1.61

 yesterday

1.50

 earlier

1.47

 wasn

1.44

 volna

1.44

 anteriormente

1.34

 damals

1.31

Activations Density 0.333%