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

    Neuronpedia

    INDEX
    Explanations

    ones identity or role in society (e.g., parent, developer, therapist) followed by personal attributes

    oai_token-act-pair · gpt-3.5-turbo

    identities and roles related to various social and professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oshenko
    -0.74
    pages
    -0.70
    umo
    -0.66
    ouls
    -0.65
    andon
    -0.64
    ntax
    -0.63
    odo
    -0.63
    NetMessage
    -0.63
    ibaba
    -0.61
    zees
    -0.60
    POSITIVE LOGITS
     myself
    1.03
     ourselves
    0.88
     educator
    0.79
     progresses
    0.76
     reviewer
    0.74
     historian
    0.73
     yourself
    0.72
     accustomed
    0.72
     certific
    0.72
     strives
    0.71
    Act Density 0.153%

    No Known Activations