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

    Neuronpedia

    INDEX
    Explanations

    places or locations in a community setting

    oai_token-act-pair · gpt-3.5-turbo

    connections to places and spaces within the community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utan
    -0.75
    oward
    -0.73
    aclysm
    -0.72
    achev
    -0.69
    rez
    -0.66
    terness
    -0.66
    factor
    -0.65
     XT
    -0.65
    atical
    -0.65
    amount
    -0.64
    POSITIVE LOGITS
     gardens
    1.02
     dining
    0.95
     rooft
    0.88
     kitchens
    0.86
     halls
    0.85
     cafes
    0.85
     parks
    0.84
     staffed
    0.83
     floors
    0.83
     restaurants
    0.83
    Act Density 0.610%

    No Known Activations