INDEX

Explanations

certain phrases or names

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

なんとなく

-1.96

もちろん

-1.84

 工場

-1.79

・・・・・・・・

-1.77

そろそろ

-1.75

今回も

-1.74

Хороший

-1.71

常に

-1.71

尚未

-1.63

 multifaceted

-1.62

POSITIVE LOGITS

3.16

鉿

2.34

,"

2.19

hsa

2.11

2.06

"",

1.98

);

1.98

 behövs

1.80

ỽ

1.78

 nakalista

1.77

Activations Density 0.055%