INDEX

Explanations

indices and counters (i, 1, 5)

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

 maji

-1.66

</h4>

-1.65

of

-1.65

 vider

-1.62

THEY

-1.61

 novi

-1.58

by

-1.57

not

-1.55

...";

-1.53

ooooooo

-1.52

POSITIVE LOGITS

ズニー

1.65

最初の

1.60

劵

1.58

 duża

1.55

してくれた

1.54

 тобой

1.52

 sesiones

1.52

 Eventually

1.52

していました

1.50

illerato

1.50

Activations Density 0.009%