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

    Neuronpedia

    INDEX
    Explanations

    descriptions of enclosed spaces

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical spaces or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Adds
    -0.75
    aclysm
    -0.72
     Rebell
    -0.70
    ocide
    -0.68
    ewitness
    -0.68
    è¦ļéĨĴ
    -0.67
    aughs
    -0.67
    icter
    -0.64
    vind
    -0.63
    itivity
    -0.63
    POSITIVE LOGITS
     desks
    1.07
    occupied
    0.97
     cramped
    0.95
     basement
    0.95
     rooms
    0.91
     seating
    0.90
    tyard
    0.89
     confines
    0.89
     Rooms
    0.88
     workspace
    0.86
    Act Density 0.830%

    No Known Activations