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

    Neuronpedia

    INDEX
    Explanations

    words related to illegal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.91
    oleon
    -0.91
    addons
    -0.79
    vation
    -0.77
    raq
    -0.75
    yrs
    -0.72
    tons
    -0.71
    winner
    -0.70
    achine
    -0.69
    sonian
    -0.69
    POSITIVE LOGITS
     downloading
    1.02
     wiret
    0.90
     detained
    0.87
     accessing
    0.86
     downloaded
    0.82
     illegally
    0.79
     obtained
    0.78
     confiscated
    0.76
     accessed
    0.76
     obtaining
    0.76
    Act Density 0.013%

    No Known Activations