Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Like" as a discourse marker

    np_acts-logits-general · gemini-2.0-flash

    like or as with phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.59
      
    -0.50
     (
    -0.46
    ↵↵
    -0.44
     X
    -0.44
    пу
    -0.43
    .
    -0.43
     Yet
    -0.42
     $
    -0.42
     yet
    -0.42
    POSITIVE LOGITS
    CloseOperation
    1.11
    تقاوى
    1.10
     Мексичка
    1.09
    ViewImports
    1.01
    ंदीखरीदारी
    0.97
     تضيفلها
    0.97
     myſelf
    0.96
    wiſe
    0.96
     $_"
    0.95
     Савезне
    0.95
    Act Density 0.197%

    No Known Activations