INDEX

Explanations

parameter

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

stro

-0.29

ä¸Ģä½ĵ

-0.28

æµģçķħ

-0.27

ÑĢÐ¾Ð½

-0.26

asts

-0.25

 cont

-0.25

éĩī

-0.24

UnderTest

-0.24

prefs

-0.24

loat

-0.24

POSITIVE LOGITS

 param

0.51

 parameter

0.50

.param

0.47

 Parameter

0.45

	param

0.44

åıĤæķ°

0.43

parameter

0.43

 schemes

0.43

 scheme

0.42

æĸ¹æ¡Ī

0.41

Activations Density 0.962%