INDEX

Explanations

descriptive states followed by details

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

ა

3.02

ו

2.95

tabPadding

2.92

ン

2.92

যুদ্ধের

2.92

فري

2.86

ATUM

2.85

ος

2.83

اتها

2.78

eredReader

2.77

POSITIVE LOGITS

go

2.72

gesteld

2.66

gal

2.64

ю

2.55

gest

2.54

σκο

2.51

ھی

2.49

gha

2.44

gar

2.43

gi

2.40

Activations Density 1.559%