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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is physically present somewhere or expressing their location

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "here."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.64
    paralle
    -0.64
    Wallet
    -0.63
    catentry
    -0.63
    acci
    -0.62
    Output
    -0.60
    Power
    -0.59
    Edge
    -0.58
    Health
    -0.58
    Meat
    -0.58
    POSITIVE LOGITS
    tical
    1.46
    tics
    1.41
    abouts
    1.22
    tic
    1.18
     illegally
    0.78
    fires
    0.75
    yers
    0.74
    adays
    0.67
    with
    0.67
    yard
    0.66
    Act Density 0.047%

    No Known Activations