INDEX

Explanations

function returns descriptions

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

 środow

1.62

ﺀ

1.56

 quedar

1.48

znam

1.47

 Melihat

1.47

 ایمان

1.47

 mettant

1.46

雯

1.46

 состо

1.46

瞋

1.44

POSITIVE LOGITS

basic

1.53

|,

1.43

lstm

1.37

idxs

1.33

algebra

1.28

ipl

1.28

,,

1.27

lbl

1.25

abbr

1.25

 basic

1.22

Activations Density 0.000%