INDEX

Explanations

exclamation marks followed by "I" or "Item"

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

ledged

2.95

纽

2.85

 AsRef

2.78

iliate

2.77

inska

2.72

ἲ

2.70

춤

2.64

sport

2.59

gitian

2.57

ijen

2.53

POSITIVE LOGITS

2.85

er

2.71

ation

2.64

اعر

2.60

ેશ

2.51

ان

2.44

橐

2.35

Rn

2.34

at

2.29

hovah

2.27

Activations Density 0.015%