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

    Neuronpedia

    INDEX
    Explanations

    terms related to railroads and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.23
    essian
    -0.17
    essa
    -0.17
    ess
    -0.16
    emean
    -0.15
    es
    -0.15
    esco
    -0.15
    yg
    -0.15
    ective
    -0.15
    emet
    -0.15
    POSITIVE LOGITS
    roads
    0.32
    road
    0.31
    ings
    0.28
    ROAD
    0.27
    iffs
    0.23
    leur
    0.23
    ors
    0.21
    ways
    0.20
    Road
    0.20
    bow
    0.19
    Act Density 0.021%

    No Known Activations