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

    Neuronpedia

    INDEX
    Explanations

    references to different types of rooms or spaces

    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
    uras
    -0.67
    pend
    -0.67
     DPR
    -0.66
    FIN
    -0.65
    alam
    -0.63
     Kickstarter
    -0.62
     Mother
    -0.61
    iago
    -0.60
    ARGET
    -0.60
    HER
    -0.60
    POSITIVE LOGITS
     doors
    0.96
    room
    0.95
    rooms
    0.87
     stalls
    0.87
     attendants
    0.81
     entrances
    0.79
     floors
    0.78
     floor
    0.76
     toilets
    0.76
    itory
    0.76
    Act Density 0.028%

    No Known Activations