INDEX

Explanations

Berg followed by names or places

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

躥

-2.73

ꙮ

-2.58

ти

-2.55

ها

-2.44

 tinge

-2.36

月初

-2.34

for

-2.30

袮

-2.30

蘗

-2.25

as

-2.20

POSITIVE LOGITS

</strong>

3.66

༵

2.77

 και

2.67

archiwizowane

2.66

și

2.56

鉿

2.55

 pasan

2.47

 goed

2.47

诸多

2.47

 dari

2.45

Activations Density 0.003%