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

    Neuronpedia

    INDEX
    Explanations

    questions and statements about actions related to games or daily life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.50
    contentLoaded
    -0.48
     further
    -0.43
    Bibliograf
    -0.41
    tanleria
    -0.41
    fycat
    -0.40
     prob
    -0.40
    AttributeSet
    -0.39
    GEBURTSDATUM
    -0.39
    béco
    -0.37
    POSITIVE LOGITS
    when
    0.76
     når
    0.75
     when
    0.73
     quando
    0.69
    cuando
    0.69
     When
    0.68
     cuando
    0.68
    quando
    0.66
     когда
    0.66
    When
    0.65
    Act Density 0.456%

    No Known Activations