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

    Neuronpedia

    INDEX
    Explanations

    phrases that express a sense of pride

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaz
    -0.74
    ura
    -0.74
    soDeliveryDate
    -0.73
    igmatic
    -0.69
    eller
    -0.67
    MX
    -0.65
    soever
    -0.65
     guiActiveUn
    -0.65
    opus
    -0.64
     accounted
    -0.64
    POSITIVE LOGITS
     what
    0.92
     how
    0.86
     sorts
    0.81
     having
    0.81
     this
    0.77
     them
    0.77
     him
    0.76
     course
    0.75
     ourselves
    0.75
     everything
    0.74
    Act Density 0.034%

    No Known Activations