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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating goals or aims

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to goals and objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culus
    -0.67
    artifacts
    -0.66
     clips
    -0.62
     Slime
    -0.62
     shred
    -0.60
    Interstitial
    -0.60
    apons
    -0.59
    orks
    -0.59
     snipp
    -0.59
    apon
    -0.59
    POSITIVE LOGITS
    Goal
    0.79
     goal
    0.74
     reason
    0.70
     takeaway
    0.69
    ical
    0.68
    iest
    0.68
    ée
    0.67
    ison
    0.67
    lessness
    0.65
     thrust
    0.65
    Act Density 0.107%

    No Known Activations