INDEX

Explanations

references to a specific person involved in scientific or art contexts

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 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

ագրություններ

-0.85

archiviato

-0.81

########.

-0.77

reportWebVitals

-0.73

+#+#

-0.71

Tikang

-0.70

Билгалдахарш

-0.68

Atsauces

-0.67

 continuant

-0.65

الدراسه

-0.65

POSITIVE LOGITS

PCL

1.00

stad

1.00

igner

0.94

etting

0.85

PCL

0.75

 bracelet

0.71

PED

0.69

irac

0.67

MISC

0.67

unes

0.67

Activations Density 0.021%