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

    Neuronpedia

    INDEX
    Explanations

    references to males

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals described as "guy" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ort
    -0.72
    tnc
    -0.72
    daily
    -0.72
    inventoryQuantity
    -0.72
    mental
    -0.71
    iff
    -0.71
    Import
    -0.69
    FW
    -0.68
    illus
    -0.68
    icut
    -0.67
    POSITIVE LOGITS
    bag
    0.80
     who
    0.80
    holes
    0.80
    bags
    0.79
    abase
    0.77
     else
    0.76
    osphere
    0.76
    gery
    0.75
     Rai
    0.75
     bru
    0.73
    Act Density 0.025%

    No Known Activations