INDEX

Explanations

states

The neuron fires on occurrences of the technical term “states” (e.g. quantum states, density of states, excited states).

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

-2.16

屺

-2.02

ing

-1.88

 fossero

-1.88

举动

-1.88

却不

-1.84

 avesse

-1.81

 décider

-1.78

 busi

-1.74

POSITIVE LOGITS

࿚

2.73

 alemán

2.30

 masih

2.16

 españolas

2.14

☫

2.08

谞

2.08

婚礼

1.98

⎽

1.97

 terminó

1.95

возмо

1.92

Activations Density 0.021%