INDEX

Explanations

ciate

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

 Appendix

-0.82

 appendix

-0.75

AndEndTag

-0.66

 ComVisible

-0.65

AccessorTable

-0.60

 Militar

-0.60

 Nemesis

-0.60

 Bant

-0.60

 overthrown

-0.59

 allocate

-0.59

POSITIVE LOGITS

ed

0.63

edo

0.52

 TextInputType

0.52

redge

0.51

dron

0.48

gráfica

0.47

 pener

0.46

ագր

0.44

proken

0.44

ever

0.44

Activations Density 0.013%