INDEX

Explanations

technical/scientific reports

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 saites

-0.52

cilis

-0.47

 filtered

-0.47

 filter

-0.47

 caminhos

-0.46

 HasFactory

-0.45

 verlie

-0.45

 väg

-0.44

Rup

-0.44

érons

-0.44

POSITIVE LOGITS

 headed

0.70

 heads

0.62

ConstraintMaker

0.59

iastes

0.59

heads

0.56

headed

0.56

 Heads

0.54

 kaarangay

0.54

Head

0.54

RegressionTest

0.54

Activations Density 0.001%