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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical locations or buildings

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of various types of facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sen
    -0.74
    uscript
    -0.74
    jin
    -0.69
    plets
    -0.69
    tail
    -0.67
    harm
    -0.67
    thin
    -0.65
    hood
    -0.64
    quel
    -0.64
    yi
    -0.64
    POSITIVE LOGITS
     facilities
    0.94
     facility
    0.86
     Facilities
    0.81
     renovations
    0.80
     utilization
    0.79
    ility
    0.77
     Facility
    0.75
     attendants
    0.74
     premises
    0.70
    ounter
    0.70
    Act Density 0.025%

    No Known Activations