INDEX

Explanations

calories

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 calories

-1.14

calories

-1.02

Calories

-1.00

 Calories

-0.93

 nakalista

-0.81

CloseOperation

-0.79

 quanta

-0.76

PERATURE

-0.75

 calorie

-0.75

 tonnage

-0.75

POSITIVE LOGITS

0.37

 produire

0.37

 alojamientos

0.36

 added

0.35

 fuir

0.35

 reír

0.34

<bos>

0.34

 takı

0.34

 Lage

0.34

 Woche

0.33

Activations Density 0.005%