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

    Neuronpedia

    INDEX
    Explanations

    terms related to spatial boundaries or limits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to constraints and boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.82
    BSD
    -0.68
    MQ
    -0.67
    Bee
    -0.65
    ãĤ¬
    -0.64
    Interested
    -0.64
    BuyableInstoreAndOnline
    -0.61
     Bunny
    -0.61
    soever
    -0.61
    downs
    -0.60
    POSITIVE LOGITS
    ruction
    0.94
    urally
    0.92
    ort
    0.92
    ented
    0.90
    itution
    0.90
    ortion
    0.88
    orial
    0.88
    uring
    0.87
    urous
    0.87
    anium
    0.86
    Act Density 0.027%

    No Known Activations