INDEX

Explanations

numbers followed by related details

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

見える

0.54

 analysts

0.52

ⵡ

0.51

 penultimate

0.47

是一名

0.47

plast

0.46

是一個

0.45

一名

0.45

膚

0.45

POSITIVE LOGITS

 Postage

0.48

itabbam

0.48

 arrivée

0.45

 Inference

0.45

 suami

0.44

 entspre

0.44

 obedience

0.43

 niezb

0.43

 Plots

0.42

 Embroidery

0.42

Activations Density 0.001%