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

    Neuronpedia

    INDEX
    Explanations

    locations or headquarters of various companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "based in" followed by a location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -1.03
    umatic
    -0.94
    xual
    -0.92
    izoph
    -0.77
     inval
    -0.77
    oeuv
    -0.75
    oglobin
    -0.74
    ilitary
    -0.73
    adder
    -0.73
     disapp
    -0.72
    POSITIVE LOGITS
     Arlington
    1.36
     Los
    1.31
     Palo
    1.31
     Pasadena
    1.31
     Wichita
    1.30
     Austin
    1.30
     Denver
    1.29
     Atlanta
    1.29
     downtown
    1.29
     Boulder
    1.29
    Act Density 0.182%

    No Known Activations