INDEX

Explanations

modulus

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

")));

-0.93

DockStyle

-0.82

 heaven

-0.81

AddTagHelper

-0.80

 calendriers

-0.78

 jsPsych

-0.75

 OnInit

-0.74

Heaven

-0.73

XmlType

-0.73

GEBURTSDATUM

-0.73

POSITIVE LOGITS

Gil

0.56

 Hard

0.51

Al

0.49

 Back

0.47

Tal

0.46

 hard

0.46

Tar

0.46

 Gran

0.45

 state

0.45

 part

0.44

Activations Density 1.581%