INDEX

Explanations

Mage or phage

np_acts-logits-general · gemini-2.5-flash-lite

The neuron detects the word "Mage" or variations related to magic users in fantasy contexts or coding references.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

This neuron is triggered by occurrences of the token “Mage” (or the uppercase variant “MAGE”), as used in Magento class names or related references.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

嗵

-3.58

ༀ

-3.28

脔

-3.23



-3.22

蕖

-3.16

⑊

-3.00

袮

-2.95

 折り

-2.86

鸝

-2.83

狁

-2.80

POSITIVE LOGITS

2.86

 There

2.84

If

2.78

2.73

2.56

 When

2.52

2.36

2.34

 Ironically

2.33

ну

2.31

Activations Density 0.003%

Mage or phage

The neuron detects the word "Mage" or variations related to magic users in fantasy contexts or coding references.

This neuron is triggered by occurrences of the token “Mage” (or the uppercase variant “MAGE”), as used in Magento class names or related references.

No Comments

No Known Activations

Mage or phage

The neuron detects the word "Mage" or variations related to magic users in fantasy contexts or coding references.

This neuron is triggered by occurrences of the token “Mage” (or the uppercase variant “MAGE”), as used in Magento class names or related references.

No Comments

No Known Activations