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

    Neuronpedia

    INDEX
    Explanations

    words related to railroads and trains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.64
    országban
    -0.61
    XmlAccessType
    -0.61
    tonsoft
    -0.61
    ControllerAdvice
    -0.59
    SCAPE
    -0.59
    исленность
    -0.59
    قایناق‌لار
    -0.58
    teness
    -0.58
    readystatechange
    -0.57
    POSITIVE LOGITS
     rail
    0.70
    Rail
    0.69
     rails
    0.64
     Train
    0.62
    rail
    0.62
     train
    0.62
     Rail
    0.62
     TRAIN
    0.62
    TRAIN
    0.59
     trains
    0.58
    Act Density 0.083%

    No Known Activations