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

    Neuronpedia

    INDEX
    Explanations

    phrases centered around sitting and being stationary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uolo
    -0.83
    ⋙
    -0.73
     Valerio
    -0.70
    })();
    -0.65
    '])){
    -0.62
     neod
    -0.61
    Durata
    -0.61
     modo
    -0.61
    ThroughAttribute
    -0.61
    tory
    -0.61
    POSITIVE LOGITS
     sit
    1.45
     Sit
    1.41
     SIT
    1.40
    Sit
    1.39
     Sitting
    1.29
    SIT
    1.27
     sits
    1.26
     sitting
    1.25
    sit
    1.19
    Sitting
    1.18
    Act Density 0.065%

    No Known Activations