INDEX

Explanations

#

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

 للاسماء

-0.73

ValueStyle

-0.69

 kasarigan

-0.67

HttpFoundation

-0.65

 Undeclared

-0.62

évaluateur

-0.62

 Tartar

-0.59

UnusedPrivate

-0.58

Билгалдахарш

-0.58

SequentialGroup

-0.57

POSITIVE LOGITS

 rule

0.59

0.57

 deliberate

0.57

 pronounce

0.49

 RULE

0.48

();)

0.48

Rule

0.48

 Rule

0.48

RULE

0.47

}}}}

0.46

Activations Density 0.017%