INDEX

Explanations

phrases following specific words

was, loans, wearing, sweating, request

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 coalesce

0.52

 escalate

0.49

д

0.48

 visceral

0.46

 abolish

0.46

 phát

0.44

 truncate

0.43

რძ

0.42

 sensibilities

0.42

발

0.42

POSITIVE LOGITS

etal

0.45

şı

0.43

behaviour

0.43

जोर

0.42

<0xDA>

0.41

ंदन

0.41

UT

0.41

ETC

0.41

UTRAL

0.41

tonne

0.41

Activations Density 0.001%