INDEX

Explanations

first word of a compound noun

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

(!__

-1.81

 homicidio

-1.70

 semua

-1.64

...."

-1.57

bazel

-1.55

全都

-1.55

']==

-1.54

 habiendo

-1.52

↵↵

-1.49

 sufri

-1.49

POSITIVE LOGITS

 them

2.47

1.89

紧接着

1.84

 régal

1.84

んご

1.80

1.78

起来的

1.72

酲

1.60

 célè

1.60

یں

1.60

Activations Density 0.211%