INDEX

Explanations

scientific properties

The neuron identifies the phrase "properties of" in scientific contexts, particularly related to chemical, physical, or mechanical characteristics of materials.

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

."

-2.36

乚

-1.98

唢

-1.91

</i>

-1.84

 facendo

-1.79

of

-1.76

 perched

-1.76

 otorga

-1.73

硨

-1.72

 насељу

-1.71

POSITIVE LOGITS

2.50

 grego

2.05

1.97

bước

1.95

полне

1.95

 rique

1.93

となりました

1.90

Достоинства

1.86

 ihre

1.85

 define

1.84

Activations Density 0.029%