INDEX

Explanations

ein followed by descriptive words

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ি

2.42

疵

2.42

spl

2.39

sup

2.28

 دیا۔

2.21

 دیا

2.14

 rewritten

2.12

nown

2.12

‌ها

2.09

kiej

2.06

POSITIVE LOGITS

atown

2.98

*"

2.93

 भंग

2.89

 пожа

2.85

 ovipares

2.85

тріш

2.73

дцать

2.73

%";

2.72

esModule

2.68

spedes

2.65

Activations Density 0.010%