INDEX

Explanations

absolute/actual

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.80

 Emits

-0.66

uxxxx

-0.64

✨:

-0.63

HostException

-0.60

pośred

-0.60

Tikang

-0.60

 arkiv

-0.59

 sjø

-0.59

autorité

-0.59

POSITIVE LOGITS

NDL

0.47

bkz

0.45

 medicine

0.45

 poisoning

0.44

 disease

0.43

 overdose

0.41

 illness

0.41

 Tuberculosis

0.41

 medicinal

0.41

 diseases

0.40

Activations Density 0.008%