INDEX

Explanations

punctuation

discount, 4-bit, Tensor, img, df

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

と思いますが

0.52

...@

0.48

ませんが

0.48

-}\

0.46

かもしれませんが

0.45

****",

0.44

 সাপ্তাহ

0.44

様専用

0.44

'=>'','

0.43

 جائیں

0.42

POSITIVE LOGITS

。

0.76

।

0.69

0.68

។

0.65

）

0.61

؟

0.57

።

0.56

۔

0.51

။

0.51

;)

0.50

Activations Density 0.310%