INDEX

Explanations

specific geographical locations

This neuron selectively activates on the word “area,” especially when it refers to a geographic or named region.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

囌

-2.22

 giocare

-2.17

 Alquiler

-2.14

iſter

-2.09

 内衣

-2.05

鼕

-2.05



-1.98



-1.96

鲥

-1.93

 meja

-1.90

POSITIVE LOGITS

2.42

2.38

of

2.14

2.08

at

2.06

st

2.06

</strong>

2.05

1.91

 sogar

1.91

 incluso

1.88

Activations Density 0.035%