INDEX

Explanations

recalling past events

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

踯

-1.51

și

-1.49

 וּ

-1.47

pesas

-1.41

他也

-1.41

 PUSTAKA

-1.38

to

-1.38

-1.33

平时

-1.32

 Their

-1.29

POSITIVE LOGITS

 Inſ

1.52

 carottes

1.44

 forcé

1.41

brite

1.38

âncias

1.38

 lavet

1.37

 punya

1.36

こともあります

1.36

 drugie

1.35

 bemerkt

1.35

Activations Density 0.004%