INDEX

Explanations

encephalo

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

ring

-0.52

sch

-0.48

dis

-0.46

sb

-0.44

了

-0.43

dis

-0.43

sta

-0.42

rs

-0.41

sj

-0.41

lit

-0.41

POSITIVE LOGITS

Autoritní

0.84

 المعيارى

0.71

omy

0.68

 للمعارف

0.65

 bezeichneter

0.63

 <=",

0.61

 onPage

0.60

omyelitis

0.60

seteq

0.59

Xer

0.59

Activations Density 0.390%