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

    Neuronpedia

    INDEX
    Explanations

    instances where actions or events are happening outside a specific location

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or events occurring outside

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.88
    sylv
    -0.82
    xml
    -0.79
    ãĤ¦ãĤ¹
    -0.73
    ħ
    -0.71
    Percent
    -0.71
    ankind
    -0.69
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
    pmwiki
    -0.69
    NF
    -0.68
    POSITIVE LOGITS
     Parliament
    1.06
     courthouse
    1.02
     Downing
    1.01
     parliament
    1.01
     Costco
    0.97
     Starbucks
    0.95
     Macy
    0.94
     Cafe
    0.92
     Embassy
    0.92
     synagogue
    0.88
    Act Density 0.130%

    No Known Activations