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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their numerical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CascadeType
    -0.76
    setcounter
    -0.66
    Considerations
    -0.65
    cloudfront
    -0.64
    riors
    -0.64
     sows
    -0.64
    уда
    -0.63
     Koper
    -0.62
    Pare
    -0.62
    gory
    -0.62
    POSITIVE LOGITS
    TagMode
    0.69
    elemField
    0.66
    ValueStyle
    0.60
    팎
    0.60
     MenuView
    0.59
    ihnachten
    0.59
    hil
    0.57
    enee
    0.56
    OrEqualTo
    0.56
     głowy
    0.55
    Act Density 0.259%

    No Known Activations