INDEX

Explanations

related to entities and their actions

The neuron activates on longer, content-heavy words (typically multi-syllable nouns or verbs).

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

ของคุณ

-1.09

嗎

-0.93

 inserted

-0.93

 whatever

-0.93

 algum

-0.91

在你

-0.89

 downloaded

-0.89

APPED

-0.88

した

-0.87

Used

-0.86

POSITIVE LOGITS

 that

3.94

ที่จะ

2.83

to

2.73

 που

1.81

 possible

1.70

for

1.69

 pouvant

1.54

 expected

1.49

 which

1.48

 که

1.48

Activations Density 0.110%