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

    Neuronpedia

    INDEX
    Explanations

    references to trains and railroad-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gham
    -0.65
     sevi
    -0.63
     Dorado
    -0.63
     bersi
    -0.62
    Tanto
    -0.61
    جوايز
    -0.60
    tory
    -0.59
    isks
    -0.58
     Siro
    -0.57
     Wolfe
    -0.56
    POSITIVE LOGITS
     trains
    1.45
     Train
    1.45
     train
    1.43
     Trains
    1.35
     TRAIN
    1.34
    Trains
    1.30
    Train
    1.29
    trains
    1.23
    TRAIN
    1.20
    train
    1.16
    Act Density 0.085%

    No Known Activations