INDEX

Explanations

for the sake of

parenthetical explanations or lists

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

 dünyanın

0.50

Nh

0.49

 eccentric

0.47

Ze

0.47

Nz

0.45

江湖

0.45

 Zhao

0.44

 thiên

0.44

Jiang

0.43

Plug

0.43

POSITIVE LOGITS

 набу

0.55

вия

0.54

 suffit

0.49

affirm

0.48

次第

0.48

ОВО

0.47

얗

0.46

numero

0.45

鋳

0.45

 reaffirm

0.44

Activations Density 0.000%