INDEX

Explanations

a handful of seemingly unrelated words

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

tvguidetime

-1.02

GraphicsUnit

-0.96

 ujednoznacz

-0.96

extAlignment

-0.94

تقاوى

-0.88

TemporalType

-0.87

LookAnd

-0.86

 ModelExpression

-0.86

 snippetHide

-0.85

 صوتيه

-0.85

POSITIVE LOGITS

Filmografie

0.52

 cose

0.47

 referenties

0.47

0.44

0.43

뀌

0.43

 continued

0.42

 cold

0.42

 wezen

0.42

Activations Density 0.218%