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

    Neuronpedia

    INDEX
    Explanations

    mentions of facilities or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific facility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plets
    -0.70
    thin
    -0.70
    corn
    -0.67
     mighty
    -0.67
    uscript
    -0.66
    tail
    -0.66
    poll
    -0.65
     decisive
    -0.64
    ohan
    -0.63
    sen
    -0.62
    POSITIVE LOGITS
     facility
    1.07
     facilities
    0.99
     Facility
    0.97
     Facilities
    0.83
    ility
    0.75
     premises
    0.72
    ilitation
    0.72
     renovations
    0.71
     annex
    0.70
    hess
    0.68
    Act Density 0.014%

    No Known Activations