INDEX

Explanations

words and phrases about relationships between people

Narrative snippets

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

expandindo

-0.60

 ujednoznacz

-0.59

RegressionTest

-0.56

MLLoader

-0.53

ühen

-0.52

 متعلقه

-0.52

 صوتيه

-0.52

Taz

-0.51

 lenker

-0.51

 Aves

-0.50

POSITIVE LOGITS

Gone

0.69

 Gone

0.66

 without

0.66

 Without

0.64

Without

0.62

AxisAlignment

0.62

Życiorys

0.61

KommentareTeilen

0.60

 Ohne

0.58

 sumpay

0.58

Activations Density 0.763%