INDEX

Explanations

symbols and expressions related to mathematical notation or formulas

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

Cav

-0.59

 Cavendish

-0.56

*/}

-0.56

+#+

-0.54

jaan

-0.53

]='\

-0.53

}*/

-0.52

mtable

-0.51

 Ciro

-0.51

Dora

-0.50

POSITIVE LOGITS

_{-

3.25

}_{-

2.64

_{-\

1.54

_{+

1.51

_{-}

1.25

}_{+

1.07

_{(

1.06

_{[

0.94

}_{(

0.93

_{+}

0.81

Activations Density 0.003%