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

    Neuronpedia

    INDEX
    Explanations

    references to locations and placements within a scene or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tunnels
    -0.17
     closets
    -0.16
     Rooms
    -0.16
     tents
    -0.16
     bedrooms
    -0.15
    ammer
    -0.15
    stadt
    -0.15
     Vaults
    -0.15
     rooms
    -0.15
    915
    -0.14
    POSITIVE LOGITS
     steps
    0.26
    steps
    0.21
     curb
    0.19
     ledge
    0.19
    Steps
    0.18
     bench
    0.18
     porch
    0.18
     sto
    0.18
     grass
    0.17
     balcony
    0.17
    Act Density 0.223%

    No Known Activations