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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-awareness and personal decision-making

    oai_token-act-pair · gpt-3.5-turbo

    references to self-identity and personal agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rought
    -0.82
    olid
    -0.75
    onite
    -0.72
    emis
    -0.69
    pour
    -0.68
    rise
    -0.68
    vals
    -0.67
    nis
    -0.67
     Syndicate
    -0.66
    orie
    -0.64
    POSITIVE LOGITS
     mate
    0.76
    Redd
    0.74
     selves
    0.73
     creatively
    0.71
    BOOK
    0.70
    selves
    0.69
    é¾įåĸļ士
    0.68
     profess
    0.68
     personally
    0.67
    imei
    0.66
    Act Density 0.051%

    No Known Activations