INDEX

Explanations

preposition after state/existence

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

álise

-1.30

archical

-1.23

 lorsqu

-1.20

celotti

-1.16

 durante

-1.12

 gefunden

-1.11

erobic

-1.10

mancy

-1.09

eci

-1.06

 mentre

-1.06

POSITIVE LOGITS

in

3.47

on

2.44

at

1.95

out

1.61

 there

1.57

 around

1.24

 هناك

1.14

 with

1.10

 inside

1.10

ở

1.05

Activations Density 0.075%