INDEX

Explanations

question words like why and qué

The neuron activates on question words meaning “why” (e.g. “¿por qué?”, “почему”, “为什么”).

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

-2.56

所有的

-2.27

⼥

-2.13

 damaging

-2.05

इटम

-2.02

ânsito

-2.00

ก็

-1.98

 tangled

-1.98

 abnormally

-1.95

POSITIVE LOGITS

↵

2.03

2.02

1.98

巾

1.91

which

1.91

CHREIB

1.80

搆

1.77

泚

1.72

LLYWOOD

1.71

<em>

1.70

Activations Density 0.002%