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

    Neuronpedia

    INDEX
    Explanations

    references to trains and related concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    müş
    -0.63
    StatusCodes
    -0.63
    ה
    -0.62
    Larry
    -0.57
    iors
    -0.56
     Larry
    -0.56
    ing
    -0.53
    ıldığı
    -0.53
     Lee
    -0.52
     scoper
    -0.52
    POSITIVE LOGITS
     Trains
    1.20
     trains
    1.20
     Train
    1.13
    Trains
    1.12
     train
    1.04
    trains
    1.04
     TRAIN
    0.97
    Train
    0.96
    ณา
    0.90
     treno
    0.88
    Act Density 0.005%

    No Known Activations