INDEX

Explanations

investigation and probe

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ticoli

-0.83

 осу

-0.82

 suatu

-0.81

 окна

-0.79

 představ

-0.78

₈

-0.78

割と

-0.76

onPress

-0.74

TypeCode

-0.74

ifflin

-0.73

POSITIVE LOGITS

 investigation

1.71

 probe

1.63

 inquiry

1.43

probe

1.34

SIT

1.30

 investigations

1.28

Probe

1.25

 investigating

1.22

 enquiry

1.22

 Probe

1.20

Activations Density 0.022%