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

    Neuronpedia

    INDEX
    Explanations

    phrases related to someone's plans or objectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to intentions and motives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ren
    -0.64
     section
    -0.62
     {{
    -0.61
    qq
    -0.61
    lete
    -0.59
     Wiz
    -0.59
    orset
    -0.59
     strain
    -0.59
    agos
    -0.58
    astic
    -0.58
    POSITIVE LOGITS
     intentions
    3.83
     motives
    2.24
     motivations
    1.90
     intent
    1.71
     aspirations
    1.71
     intention
    1.69
     Intent
    1.67
     ambitions
    1.66
     sentiments
    1.53
    intent
    1.52
    Act Density 0.010%

    No Known Activations