INDEX

Explanations

references to a specific authoritative organization or authority figure

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

tizing

-0.70

éric

-0.55

vá

-0.53

ään

-0.53

 MULTI

-0.52

zyg

-0.50

 ense

-0.50

TAGS

-0.50

CRETE

-0.48

 multi

-0.48

POSITIVE LOGITS

 Authority

1.65

Authority

1.04

 AUTHORITY

1.01

odeficiency

0.98

 Obrador

0.77

AUTHOR

0.74

GrantedAuthority

0.74

 leasing

0.73

OGND

0.73

theorem

0.71

Activations Density 0.006%