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

    Neuronpedia

    INDEX
    Explanations

    keywords related to trains and transportation infrastructure

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nicolas
    -0.77
     roberto
    -0.74
     hek
    -0.70
     alberto
    -0.68
     gabri
    -0.67
     fortn
    -0.66
     lara
    -0.65
     kaos
    -0.64
     purcha
    -0.64
     sergio
    -0.63
    POSITIVE LOGITS
     train
    1.52
    train
    1.39
     Train
    1.34
     trains
    1.32
    Train
    1.32
     TRAIN
    1.14
     Trains
    1.10
    TRAIN
    1.09
    Trains
    1.06
    trains
    1.05
    Act Density 0.051%

    No Known Activations