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

    Neuronpedia

    INDEX
    Explanations

    references to metro and subway stations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wind
    -0.53
     dét
    -0.50
    winding
    -0.49
     malo
    -0.47
     winds
    -0.46
     nakalista
    -0.46
    LogFactory
    -0.44
     wound
    -0.44
    lecular
    -0.43
    Preconditions
    -0.43
    POSITIVE LOGITS
     subway
    1.01
     Metro
    0.87
     train
    0.83
     station
    0.83
     trains
    0.81
    🚇
    0.81
     metro
    0.81
    Metro
    0.81
    Subway
    0.80
     метро
    0.80
    Act Density 0.259%

    No Known Activations