INDEX

Explanations

already

The neuron strongly activates on mentions of people affected or involved in a violent incident—especially words like “victims,” “police,” and “officers.”

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

׳

-0.93

 určit

-0.90

eping

-0.89

ese

-0.88

timeScale

-0.85

 Особенно

-0.82

ubber

-0.82

 cierto

-0.81

 dimost

-0.80

ity

-0.80

POSITIVE LOGITS

 already

3.64

Already

2.72

already

2.59

 Already

2.50

 уже

2.47

 bereits

2.25

 już

2.23

ALREADY

2.14

 ALREADY

2.13

 allerede

2.11

Activations Density 0.071%