INDEX

Explanations

that/those demonstratives

that's a word

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

this

0.77

 denna

0.71

 denne

0.70

 tohoto

0.64

 هذا

0.63

 මෙය

0.62

as

0.60

これを

0.59

 questo

0.59

these

0.58

POSITIVE LOGITS

 pesky

0.75

 그거

0.67

걔

0.65

 εκεί

0.59

在那

0.59

那個

0.57

那个

0.57

那样

0.56

 거기

0.56

那里

0.55

Activations Density 0.370%