INDEX

Explanations

conditional explanations and examples

example usage

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

 والم

0.38

 Estoy

0.37

and

0.36

 Gera

0.36

และ

0.35

 będ

0.35

几

0.34

 Sekret

0.33

 وت

0.33

拥

0.33

POSITIVE LOGITS

 když

0.42

 例えば

0.40

example

0.38

 एग्जांपल

0.37

例えば

0.37

 ਤੁਸੀਂ

0.37

 ECONOMIC

0.36

 ejemplo

0.36

 example

0.35

ತಕ್ಕ

0.35

Activations Density 0.000%