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

    Neuronpedia

    INDEX
    Explanations

    phrases that express cynicism or criticism towards societal issues and leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RuleContext
    -0.62
    ///</
    -0.53
     ExecuteAsync
    -0.53
     poil
    -0.53
    quakes
    -0.51
    makeText
    -0.51
    devel
    -0.51
    Zitat
    -0.50
    punkten
    -0.49
    ★★★★☆
    -0.49
    POSITIVE LOGITS
    siao
    0.54
     industriale
    0.49
     Empieza
    0.48
     sold
    0.48
    ToAction
    0.46
    ftagPool
    0.46
    lectual
    0.46
     faibles
    0.46
     passively
    0.44
     naï
    0.44
    Act Density 0.351%

    No Known Activations