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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to groups of people connected by certain characteristics or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.79
     ModelExpression
    -0.65
    PerformLayout
    -0.62
    ArgumentParser
    -0.60
    ⓧ
    -0.60
    XmlAccessType
    -0.59
    styleType
    -0.58
    VIAF
    -0.57
     resourceCulture
    -0.56
    utilisons
    -0.52
    POSITIVE LOGITS
     quienes
    0.81
     people
    0.72
     Those
    0.71
     Whoever
    0.70
    those
    0.69
    Those
    0.69
     those
    0.69
    Whoever
    0.69
     whoever
    0.64
     którzy
    0.64
    Act Density 0.250%

    No Known Activations