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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different types of rooms, especially those associated with specific activities or functions

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of rooms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FIN
    -0.69
    alam
    -0.67
    pend
    -0.67
    JUST
    -0.65
    HER
    -0.65
    uras
    -0.64
     Mother
    -0.63
     Kickstarter
    -0.60
     DPR
    -0.60
     reconnect
    -0.58
    POSITIVE LOGITS
    room
    1.05
    rooms
    0.97
     doors
    0.96
     stalls
    0.82
     attendants
    0.79
    itory
    0.79
     floor
    0.78
    stairs
    0.78
     rooms
    0.77
     entrances
    0.76
    Act Density 0.022%

    No Known Activations