INDEX

Explanations

mathematical expressions and symbols

This neuron activates on occurrences of a variable or function name immediately followed by an open parenthesis, a single‐letter argument, and a closing parenthesis (e.g. s(y), k(t), u(c)).

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

Distribución

-1.30

Causas

-1.27

шению

-1.21

&#

-1.19

anzeigen

-1.18

brille

-1.18

㌧

-1.16

푉

-1.16

名前

-1.13

😕

-1.13

POSITIVE LOGITS

就可以了

1.34

就行了

1.31

就好了

1.25

才行

1.24

 każde

1.13

 например

1.09

日発売

1.09

就行

1.07

грі

1.05

autre

1.03

Activations Density 0.046%