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

    Neuronpedia

    INDEX
    Explanations

    references to communal living arrangements, particularly in dormitory settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seats
    -0.16
    mouseleave
    -0.15
    camp
    -0.14
    æł¡
    -0.14
    argin
    -0.14
    iaux
    -0.14
    ervals
    -0.14
    isan
    -0.13
    Degrees
    -0.13
    ancel
    -0.13
    POSITIVE LOGITS
     residents
    0.35
     Residents
    0.34
     Resident
    0.32
    Residents
    0.32
     hall
    0.30
     Residence
    0.30
     resident
    0.29
     residence
    0.29
     housing
    0.28
     living
    0.28
    Act Density 0.014%

    No Known Activations