INDEX

Explanations

Word fragments and URLs

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

MEN

-0.69

icana

-0.68

ica

-0.63

 fumée

-0.62

 fédé

-0.59

 bienfaits

-0.59

ican

-0.57

 enfans

-0.57

 émissions

-0.56

mena

-0.56

POSITIVE LOGITS

PerformLayout

0.76

 Ouverture

0.76

 Chwiliwch

0.74

abetes

0.71

 nahilalakip

0.69

DebuggerStep

0.67

SourceChecksum

0.64

wahati

0.63

Rtl

0.62

SequentialGroup

0.62

Activations Density 0.053%