INDEX

Explanations

sameness and comparison

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

を

-1.68

of

-1.60

もちろん

-1.38

<bos>

-1.35

つまり

-1.34

ที่มา

-1.32

but

-1.31

<0xA3>

-1.30

調味料

-1.27

薔薇

-1.25

POSITIVE LOGITS

 same

1.88

ところに

1.27

ようだ

1.27

corrhi

1.23

ologies

1.21

1.20

mismo

1.17

 SAME

1.17

様な

1.16

感じで

1.16

Activations Density 0.125%