INDEX

Explanations

disabled people and groups

The neuron activates on mentions of disability, specifically the word “disabled” (and its close variants) referring to people with disabilities.

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

-2.81

蓠

-2.61

indelijk

-2.58

⩤

-2.47

líben

-2.39

pitched

-2.25

 είναι

-2.23

 bliss

-2.22

犼

-2.22

 моей

-2.20

POSITIVE LOGITS

2.88

what

2.77

۹

2.55

而

2.53

Finally

2.42

If

2.38

There

2.31

These

2.31

with

2.31

да

2.31

Activations Density 0.011%