INDEX

Explanations

the word "even" in mathematical text

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 even

-2.53

even

-2.13

Even

-1.82

 EVEN

-1.80

 Even

-1.75

 incluso

-1.73

 даже

-1.72

EVEN

-1.68

 навіть

-1.67

Incluso

-1.65

POSITIVE LOGITS

 fiche

0.49

Namara

0.47

0.43

 Coyle

0.43

 Hendricks

0.43

 pār

0.42

و

0.42

 cerchi

0.42

 member

0.41

觉

0.41

Activations Density 0.150%