INDEX

Explanations

actors starring in films

The neuron detects mentions of film credits—particularly occurrences of “star,” “stars,” and similar cast/crew credit terms.

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

 къде

-1.68

 clínicas

-1.67

兩

-1.63

///</

-1.56

}_{

-1.52

 gewöhnlich

-1.52

 Käufer

-1.48

jangkau

-1.47

 help

-1.46

They

-1.43

POSITIVE LOGITS

ться

1.74

 incomparable

1.48

 legiti

1.46

鹟

1.45

黢

1.45

 pemuda

1.45

exe

1.45

岨

1.44

但

1.44

1.43

Activations Density 0.015%