INDEX

Explanations

this neuron seems to activate on a variety of scientific and mechanical topics

connecting different topics

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

Negative Logits

 للمعارف

-0.96

הערות

-0.69

 EconPapers

-0.66

enterOuterAlt

-0.63

DEFINITIONS

-0.59

 eventdata

-0.56

getMenuInflater

-0.54

 שוליים

-0.54

脚注の使い方

-0.53

 كومونز

-0.52

POSITIVE LOGITS

fl

0.60

 betweenstory

0.59

IsContent

0.57

 onCreateView

0.56

IsMutable

0.55

 Lives

0.54

InitVars

0.52

 pounds

0.51

 lives

0.49

exh

0.49

Activations Density 3.244%