INDEX

Explanations

deserve credit or attention

The neuron detects expressions of deserving or entitlement (words like deserve, entitled, praise, etc.).

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

 autres

-1.49

 affect

-1.32

 autre

-1.29

好事

-1.27

 Effekt

-1.25

 anderen

-1.24

our

-1.23

 otras

-1.22

 poderos

-1.21

 других

-1.20

POSITIVE LOGITS

 which

1.36

 when

1.29

這個

1.14

Ṇ

1.13

れます

1.13

guiar

1.13

圳

1.12

ry

1.10

 CHIN

1.10

씻

1.09

Activations Density 0.019%