INDEX

Explanations

Proportion Determination

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

razole

2.60

Dif

2.59

VICES

2.53

χύ

2.51

ități

2.47

μένος

2.43

輿

2.42

pruch

2.42

្រ

2.39

்சி

2.37

POSITIVE LOGITS

腊

2.61

fare

2.35

ir

2.29

ട്ട

2.25

usiasm

2.24

정에

2.22

臘

2.22

慾

2.11

 renverse

2.10

factorial

2.08

Activations Density 0.004%