INDEX

Explanations

aj kh ances ance au ij jan amm asa 4

professions and actions

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

د

0.52

 sogno

0.51

я

0.51

 Stoll

0.48

ен

0.46

 preoccup

0.45

 subordination

0.45

叛

0.45

 pursue

0.44

 piace

0.44

POSITIVE LOGITS

aj

0.56

kh

0.54

ances

0.53

ance

0.52

au

0.51

ij

0.50

jan

0.50

amm

0.49

asa

0.48

Activations Density 0.002%