INDEX

Explanations

to followed by action 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

in

-1.96

↵

-1.81

by

-1.80

 after

-1.76

for

-1.62

at

-1.59

 some

-1.58

नलोड

-1.55

 when

-1.53

我了

-1.42

POSITIVE LOGITS

茈

2.06

 perpé

1.68

1.66

 uniquement

1.65

 attirer

1.65

 Preisen

1.61

 男の子

1.60

 駅前

1.59

 durer

1.58

 Erkrank

1.57

Activations Density 0.016%