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

    Neuronpedia

    INDEX
    Explanations

    terms related to railways and railroad transportation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Railway
    -0.25
     Rail
    -0.24
     railways
    -0.23
    éīĦéģĵ
    -0.21
    Rail
    -0.21
     railway
    -0.21
     railroad
    -0.21
     Train
    -0.20
     rail
    -0.20
    rail
    -0.20
    POSITIVE LOGITS
    roads
    0.31
    ways
    0.26
    way
    0.24
    cars
    0.24
    car
    0.24
    ings
    0.24
    bed
    0.23
     lines
    0.23
    ro
    0.20
     line
    0.20
    Act Density 0.018%

    No Known Activations