INDEX

Explanations

unique conceptual fingerprint

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

uw

1.08

1.06

je

1.04

om

1.02

soo

1.01

 compliments

1.01

о

1.01

да

1.01

yh

1.01

 pati

1.01

POSITIVE LOGITS

聒

1.49

श्विक

1.37

ூல்

1.34

 pernicious

1.28

Estado

1.26

<unused537>

1.25

 nefarious

1.24

াইলেন

1.24

 जायेगी

1.24

轱

1.23

Activations Density 0.088%