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

    Neuronpedia

    INDEX
    Explanations

    words related to transportation infrastructure, such as railways and projects

    oai_token-act-pair · gpt-3.5-turbo

    references to light rail systems and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aroo
    -0.81
    FactoryReloaded
    -0.68
     Dhabi
    -0.64
    rency
    -0.63
    >>\
    -0.63
    çĭ
    -0.62
    ãĥĥãĥī
    -0.62
     Zar
    -0.62
    ties
    -0.61
    legate
    -0.61
    POSITIVE LOGITS
    elight
    0.97
     lamps
    0.87
     candles
    0.85
     torches
    0.81
    dark
    0.79
    reflect
    0.79
    oresc
    0.78
    ech
    0.77
     candle
    0.75
    skinned
    0.75
    Act Density 0.159%

    No Known Activations