INDEX

Explanations

string literals in code

The neuron is triggered by numeric tokens (numbers or numerals) in the text.

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

 also

-1.51

 także

-1.47

 allmäh

-1.43

 también

-1.42

がありますが

-1.40

 trochę

-1.38

 semelhante

-1.38

 גם

-1.37

intégration

-1.34

queles

-1.31

POSITIVE LOGITS

 توانند

1.43

})->

1.35

 ſay

1.27

 bertemu

1.24

iteten

1.23

}_{

1.23

bundet

1.23

！

1.22

Pokud

1.20

kå

1.20

Activations Density 0.036%