INDEX

Explanations

I followed by verbs

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

 también

-0.97

 επίσης

-0.88

 também

-0.87

 also

-0.86

 पनि

-0.85

Bad

-0.85

Also

-0.85

 agree

-0.84

oved

-0.83

Le

-0.82

POSITIVE LOGITS

 will

1.52

 apologize

1.19

 apologies

1.15

won

1.10

 wont

1.09

 opět

1.07

 mentioned

1.05

 hesitated

1.05

 nebude

1.04

 shall

1.03

Activations Density 0.069%