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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locations and positioning within a scene

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edis
    -0.17
    rooms
    -0.16
     Rooms
    -0.15
    ibase
    -0.15
    ammer
    -0.15
    umbo
    -0.15
    stadt
    -0.15
     tunnels
    -0.14
    rab
    -0.14
     closets
    -0.14
    POSITIVE LOGITS
     steps
    0.26
     bench
    0.24
     platform
    0.22
     curb
    0.21
    steps
    0.21
     ledge
    0.21
    Steps
    0.20
     porch
    0.19
     stool
    0.19
     sto
    0.19
    Act Density 0.212%

    No Known Activations