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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people, places, and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.66
    aeper
    -0.66
     crust
    -0.65
     depleted
    -0.64
     carbohyd
    -0.64
     redistributed
    -0.64
     soluble
    -0.63
    ographically
    -0.63
    ataka
    -0.62
    ohyd
    -0.62
    POSITIVE LOGITS
     Hotel
    1.38
     Stadium
    1.32
     Hospital
    1.31
     Resort
    1.30
     Theatre
    1.26
     Studios
    1.22
     Theater
    1.21
     Mansion
    1.21
     Airport
    1.20
     Chapel
    1.15
    Act Density 0.306%

    No Known Activations