INDEX

Explanations

my/your/its/their own

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

cún

-1.16

 chegar

-1.14

に行った

-1.13

 podría

-1.08

 parfois

-1.06

igts

-1.05

 souvent

-1.04

 publicó

-1.02

Pb

-1.01

嗑

-1.01

POSITIVE LOGITS

own

3.42

 itself

1.88

自己

1.73

 sendiri

1.72

自己的

1.66

 propia

1.64

自身

1.64

 próprio

1.61

 соб

1.59

 propio

1.58

Activations Density 0.039%