INDEX

Explanations

relationships

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 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

ViewFeatures

-0.83

 onOptions

-0.79

spesies

-0.69

 архивлан

-0.68

alyptus

-0.66

 stretcher

-0.66

SizeF

-0.66

 Infórmanos

-0.65

 Stretcher

-0.65

 pearls

-0.64

POSITIVE LOGITS

Pro

0.46

pro

0.45

 Trust

0.44

Pro

0.42

Trust

0.40

EL

0.39

 confiance

0.39

googleapis

0.38

彿

0.37

Cat

0.36

Activations Density 0.017%