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

    Neuronpedia

    INDEX
    Explanations

    places or locations related to transportation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Station."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.73
    Downloadha
    -0.71
    assic
    -0.71
    oiler
    -0.68
    ãĥ£
    -0.68
    paces
    -0.67
    theless
    -0.66
    ortium
    -0.65
    aphael
    -0.65
    umers
    -0.62
    POSITIVE LOGITS
     Station
    1.27
    Station
    1.02
    eering
    0.88
    eers
    0.87
     station
    0.84
    wagon
    0.83
    station
    0.82
     stations
    0.81
     Depot
    0.79
    DB
    0.77
    Act Density 0.012%

    No Known Activations