INDEX

Explanations

relationship between

This neuron activates on numeric quantities (e.g., integers or decimals).

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

."

-1.93

esa

-1.48

缡

-1.40

:'

-1.39

".

-1.39

'][]

-1.38

})-\

-1.38

inspace

-1.37

 ندار

-1.35

!=

-1.34

POSITIVE LOGITS

its

2.13

 your

1.86

橚

1.73

 Dijo

1.59

 procesu

1.59

lahir

1.52

 powodu

1.48

んじゃ

1.47

ѹ

1.46

 uwagi

1.45

Activations Density 0.073%