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

    Neuronpedia

    INDEX
    Explanations

    mention of specific goals or aims in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the aims or goals of projects and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Solitaire
    -0.71
    Interstitial
    -0.69
    culus
    -0.68
    artifacts
    -0.68
    flush
    -0.63
     Slime
    -0.62
    ilver
    -0.61
    Lot
    -0.60
    cold
    -0.59
    Magic
    -0.58
    POSITIVE LOGITS
     goal
    0.79
    Goal
    0.78
    lessness
    0.71
    orial
    0.70
    iest
    0.70
     Goal
    0.69
     reason
    0.68
    lessly
    0.68
     promoter
    0.67
     lesson
    0.67
    Act Density 0.113%

    No Known Activations