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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of reality

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "reality" and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucky
    -0.87
    tein
    -0.81
    edo
    -0.79
    incinn
    -0.77
    asus
    -0.76
    kers
    -0.75
    edin
    -0.74
    asso
    -0.74
    ongh
    -0.74
    oyal
    -0.73
    POSITIVE LOGITS
     TV
    0.85
    ually
    0.83
    ignment
    0.83
    psons
    0.83
     tv
    0.80
     check
    0.79
    istically
    0.78
     Ens
    0.77
     Lange
    0.76
     conformity
    0.75
    Act Density 0.029%

    No Known Activations