INDEX

Explanations

locations and states

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

 faciliter

-1.80

 diriger

-1.70

𓆏

-1.60

睃

-1.60

 appels

-1.57

 fonctionnalités

-1.55

titial

-1.55

 bascul

-1.54

CHREIB

-1.54

 lèvres

-1.54

POSITIVE LOGITS

for

1.84

↵↵

1.80

 providing

1.55

 after

1.53

 Although

1.45

at

1.42

↵

1.38

⦑

1.38

 although

1.37

 Despite

1.37

Activations Density 0.028%