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

    Neuronpedia

    INDEX
    Explanations

    locations, particularly train stations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marketable
    -0.69
    erenn
    -0.64
    ojure
    -0.64
    usalem
    -0.63
    URES
    -0.63
    ":"/
    -0.61
    aphael
    -0.61
    IGHTS
    -0.61
     nerv
    -0.61
    STEM
    -0.60
    POSITIVE LOGITS
     wagon
    1.08
    ery
    1.02
     station
    0.93
     stations
    0.90
    wagon
    0.89
     attendant
    0.84
    arity
    0.82
    ation
    0.81
    pole
    0.77
    eering
    0.76
    Act Density 0.071%

    No Known Activations