INDEX

Explanations

a

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NameInMap

-0.87

 الرياضيه

-0.71

zbęd

-0.64

省市镇

-0.64

 للمعارف

-0.63

 &___

-0.63

UnusedPrivate

-0.62

IUrlHelper

-0.58

posedge

-0.58

 '\\;'

-0.57

POSITIVE LOGITS

 single

0.63

 fewer

0.59

 different

0.54

 избран

0.51

}`).

0.50

single

0.50

 einzelne

0.49

 SINGLE

0.49

alpa

0.47

0.46

Activations Density 0.002%