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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "down."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollectionView
    -0.78
     '\\;'
    -0.77
    각주
    -0.74
     tartalomajánló
    -0.74
    HandlerContext
    -0.73
    الحياه
    -0.70
    WriteLiteral
    -0.69
    Hauptartikel
    -0.67
     nahilalakip
    -0.67
     Fras
    -0.65
    POSITIVE LOGITS
     down
    1.22
     DOWN
    0.87
    down
    0.87
    DOWN
    0.85
    Down
    0.81
     Down
    0.75
     downs
    0.68
    downs
    0.67
    ocere
    0.67
    kommen
    0.64
    Act Density 0.076%

    No Known Activations