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

    Neuronpedia

    INDEX
    Explanations

    terms related to trains and locomotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enger
    -0.17
    erland
    -0.16
    agra
    -0.16
    ippi
    -0.15
    ying
    -0.15
    empo
    -0.15
    meric
    -0.15
    ERRUPT
    -0.15
    infeld
    -0.14
    igger
    -0.14
    POSITIVE LOGITS
    otive
    0.41
    ot
    0.33
     engines
    0.27
    otor
    0.26
     motive
    0.25
     Engines
    0.25
     engine
    0.24
    otion
    0.24
     motors
    0.22
     pulls
    0.22
    Act Density 0.003%

    No Known Activations