INDEX

Explanations

Matt followed by surname

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

er

-2.67

которые

-2.52

 finds

-2.45

 establecidas

-2.23

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-2.14

 interessante

-2.11

↵↵↵↵↵↵↵↵↵↵↵↵↵

-2.09

le

-2.08

_{

-2.06

 Their

-2.06

POSITIVE LOGITS

筇

2.89

2.64

他现在

2.56

咴

2.45

他知道

2.41

 развитии

2.41

坶

2.33

缛

2.31

身边的

2.30

他能

2.25

Activations Density 0.004%