INDEX

Explanations

references to legal or judicial decisions grounded in law

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

addPreferredGap

-0.69

 Pingback

-0.57

Czytaj

-0.54

zied

-0.52

 cuesta

-0.50

 تانيه

-0.50

 werfen

-0.50

vese

-0.49

Ӕ

-0.49

velg

-0.48

POSITIVE LOGITS

 grounded

3.31

grounded

2.72

 grounding

2.31

Grounded

1.70

 rooted

1.34

rooted

1.09

 stranded

0.91

 anchored

0.91

stranded

0.69

AccessorTable

0.68

Activations Density 0.004%