INDEX

Explanations

confirmation questions

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

 ??????

-1.47

…」

-1.46

 ?????

-1.45

.*;

-1.40

 astounding

-1.37



-1.37

僦

-1.34

 Notwendigkeit

-1.33

 ludicrous

-1.30

閖

-1.30

POSITIVE LOGITS

7.78

?"

3.41

?”

3.38

؟

3.05

?)

2.64

？

2.55

2.25

?}

2.05

?!

2.03

՞

1.93

Activations Density 1.477%