INDEX

Explanations

performances on a stage

The neuron is triggered by mentions of being on stage or in a live‐performance context (e.g. “on stage,” “stage”).

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

俢

-1.96

-1.91

-1.88

></

-1.87

攆

-1.82

-1.74

-1.73

𝐙

-1.72

’

-1.69

POSITIVE LOGITS

 необходимости

1.98

 этими

1.89

一台

1.80

 nacimiento

1.80

1.79

 ของ

1.76

 если

1.74

 dificultades

1.73

 stage

1.73

椒

1.70

Activations Density 0.009%