INDEX

Explanations

explanations and lists

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

ביע

2.87

 strait

2.85

γωγ

2.81

ombrie

2.79

isValue

2.77

σταν

2.73

𠃌

2.62

 ГӀ

2.60

нци

2.59

 。,

2.58

POSITIVE LOGITS

णिज्य

3.54

onload

2.84

es

2.57

ahoo

2.53

afa

2.48

etting

2.44

2.43

imbledon

2.43

aw

2.42

urst

2.38

Activations Density 2.614%