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

    Neuronpedia

    INDEX
    Explanations

    phrases related to goals, tasks, and priorities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate primary goals or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quila
    -0.79
    apons
    -0.69
    uyomi
    -0.68
    robe
    -0.67
    miah
    -0.67
    ocket
    -0.67
     Unsure
    -0.65
    estyles
    -0.65
    onyms
    -0.65
    imei
    -0.65
    POSITIVE LOGITS
     hers
    0.87
     ours
    0.81
     sorts
    0.81
     theirs
    0.76
     adolescence
    0.74
     mine
    0.74
     yours
    0.70
     course
    0.67
     contention
    0.67
     deterrence
    0.67
    Act Density 0.177%

    No Known Activations