INDEX

Explanations

academic disciplines

This neuron activates on mentions of “social science” or “social sciences.”

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

-2.09

崀

-1.53



-1.44

给予

-1.43

 nube

-1.41

 converted

-1.41

一旁

-1.40

 repens

-1.36

 reutiliz

-1.35

吳

-1.35

POSITIVE LOGITS

also

1.66

1.64

\&

1.63

èrent

1.60

it

1.55

.";

1.54

 завжди

1.51

.".

1.48

1.47

Activations Density 0.013%