INDEX

Explanations

the word "event", especially in the context of code

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

 Happen

-0.90

happens

-0.86

Happ

-0.83

 happen

-0.82

 happens

-0.81

 suceder

-0.81

 happening

-0.81

 HAPP

-0.81

happen

-0.80

 Exactly

-0.75

POSITIVE LOGITS

варь

0.75

 lenker

0.74

 EVENT

0.72

event

0.69

 Event

0.69

 Events

0.68

 Welsh

0.68

 event

0.67

 boyunca

0.67

벤트

0.66

Activations Density 0.026%