INDEX

Explanations

understanding what it means or takes

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



-2.27

𖧵

-2.11

ᕱ

-2.05

४

-1.84

kurtka

-1.80

狁

-1.76

 preparados

-1.73

瓛

-1.72

 alojamientos

-1.71

 decorados

-1.70

POSITIVE LOGITS

2.31

of

2.23

You

2.08

for

1.96

In

1.86

and

1.84

er

1.84

 That

1.69

 about

1.68

—

1.64

Activations Density 0.011%