INDEX

Explanations

version numbers and dates

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

🫃

-1.61

 italiens

-1.59

🧌

-1.59

 жк

-1.54

-1.50

‌آم

-1.48

”،

-1.46

(),

-1.43

}$,

-1.41

',

-1.39

POSITIVE LOGITS

 после

1.84

 after

1.81

 even

1.73

tionally

1.56

−/−

1.53

銓

1.52

 Если

1.52

raisers

1.48

 dozens

1.47

1.45

Activations Density 0.039%