INDEX

Explanations

command line execution

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

iš

2.18

 falls

2.09

respect

2.03

ing

1.98

시아

1.96

mis

1.95

ت

1.91

erit

1.91

賁

1.86

pods

1.84

POSITIVE LOGITS

__(/*!

2.80

chés

2.74

賬

2.63

бек

2.61

pherd

2.60

瘩

2.59

账

2.58

ഗീയ

2.49

製

2.49

logne

2.49

Activations Density 0.303%