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

    Neuronpedia

    INDEX
    Explanations

    references to train stations or railway stations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entic
    -0.17
    tings
    -0.17
    ustin
    -0.16
    anko
    -0.16
    UAL
    -0.16
    IES
    -0.15
    ksi
    -0.15
    ÑĩнÑĸ
    -0.15
    оÑĨи
    -0.15
    lesh
    -0.14
    POSITIVE LOGITS
    nement
    0.33
    ary
    0.33
    ery
    0.33
    arity
    0.29
    aries
    0.21
    ality
    0.21
    naire
    0.21
    ARY
    0.20
    wagon
    0.19
    ERY
    0.19
    Act Density 0.017%

    No Known Activations