INDEX

Explanations

map contexts in programming

The neuron strongly activates on occurrences of the token “map” (in any casing or as part of identifiers/file names).

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

</sup>

-2.16

</h2>

-2.05

狨

-1.71

та

-1.63

}$,

-1.63

_{

-1.56

テ

-1.51

 détaillés

-1.48

 حتی

-1.48

xffff

-1.47

POSITIVE LOGITS

 this

2.11

 three

2.05

 both

1.95

 many

1.90

two

1.88

瑧

1.88

 from

1.84

Its

1.80

 dozens

1.78

 hundreds

1.77

Activations Density 0.014%