INDEX

Explanations

entertaining and fun

abuse, cruelty, and attacks

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

 רק

0.43

 hearers

0.43

앱

0.42

 uży

0.42

 pakai

0.42

 ถ้า

0.41

Է

0.41

 simples

0.40

 சிகிச்ச

0.40

 இருந்தால்

0.40

POSITIVE LOGITS

and

0.60

),”

0.58

&/

0.58

و

0.57

0.56

ও

0.56

และ

0.55

и

0.54

và

0.54

 και

0.51

Activations Density 0.001%