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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal intentions or goals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express intentions, goals, or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.74
    idates
    -0.68
    ierrez
    -0.63
     yourselves
    -0.63
    ikhail
    -0.62
    endez
    -0.61
    -+-+
    -0.60
    ãħĭ
    -0.58
    ãĤª
    -0.58
     Leone
    -0.57
    POSITIVE LOGITS
     colleague
    0.76
    husband
    0.74
    favorite
    0.73
    ventures
    0.72
     thesis
    0.68
    stic
    0.68
     myself
    0.67
     planner
    0.67
    collection
    0.66
    arest
    0.66
    Act Density 0.252%

    No Known Activations