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

    Neuronpedia

    INDEX
    Explanations

    references to various types of stations and stationery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dibles
    -0.87
    ]--;
    -0.82
    ]))
    -0.80
    goog
    -0.78
     CWE
    -0.78
     Perse
    -0.76
    RTLE
    -0.74
    dics
    -0.73
     Eri
    -0.73
    %)$
    -0.72
    POSITIVE LOGITS
     stations
    1.80
     station
    1.72
     Station
    1.67
     Stations
    1.59
     STATION
    1.58
    Station
    1.57
    Stations
    1.53
    stations
    1.46
    STATION
    1.44
    station
    1.36
    Act Density 0.093%

    No Known Activations