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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical spaces and environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     driveway
    -0.19
     fences
    -0.17
     fence
    -0.17
     Intr
    -0.16
     campuses
    -0.16
     Campus
    -0.15
     campground
    -0.15
     festivals
    -0.14
     doorstep
    -0.14
     parks
    -0.14
    POSITIVE LOGITS
     room
    0.69
     rooms
    0.59
     Room
    0.58
    room
    0.57
     ROOM
    0.53
    Room
    0.52
    -room
    0.51
     Rooms
    0.48
    rooms
    0.47
    _room
    0.47
    Act Density 0.422%

    No Known Activations