INDEX

Explanations

box_sizing or box-shadow

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

-2.88



-2.38

 verbeter

-2.16

ться

-2.09

 města

-2.06

 oppervlak

-2.06

 have

-2.05

を利用

-2.03

 kwamba

-2.02

 kazak

-1.99

POSITIVE LOGITS

2.69

𖣔

2.58

 ก็

2.55

2.36

Зно

2.30

2.25

2.17

瑒

2.11

2.08

 осторо

2.06

Activations Density 0.029%