INDEX

Explanations

The neuron strongly activates on the very first word of each new post or section (i.e. sentence-initial, capitalized tokens).

sentence beginnings

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

Leírás

-1.35

 Lakukan

-1.29

توضیحات

-1.29

 великолеп

-1.27

 Pastikan

-1.25

Kelas

-1.24

りましたが

-1.24

😕

-1.23

öf

-1.20

 quartiere

-1.18

POSITIVE LOGITS

1.72

</b>

1.46

1.34

就可以了

1.33

1.31

 amanhã

1.24

↵↵↵

1.23

↵↵↵↵

1.16

を書く

1.14

自体は

1.14

Activations Density 0.042%