INDEX

Explanations

references to tables or figures

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

]}>

-0.86

 Tren

-0.79

'">

-0.78

 Macmillan

-0.74

apollo

-0.74

="#"><

-0.74

andrea

-0.73

)">

-0.72

__":

-0.72

Tren

-0.71

POSITIVE LOGITS

 Béla

0.79

hyung

0.78

 Bela

0.78

 msglen

0.75

newArray

0.74

posedge

0.73

Rha

0.72

rinth

0.71

 autorytatywna

0.71

xase

0.71

Activations Density 0.020%