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

    Neuronpedia

    INDEX
    Explanations

    references to railways or railroads

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    argb
    -0.69
    fromCharCode
    -0.69
    MeasureSpec
    -0.68
     asum
    -0.64
     diarias
    -0.64
    Captor
    -0.63
    piram
    -0.63
    vdash
    -0.62
    ziv
    -0.61
     Rina
    -0.59
    POSITIVE LOGITS
     railway
    1.36
     railways
    1.28
    railway
    1.23
    Railway
    1.22
     Railway
    1.21
     railroad
    1.19
     railroads
    1.19
     Railways
    1.14
     Railroad
    1.13
     RAILWAY
    1.08
    Act Density 0.009%

    No Known Activations